- title: 'Temporal aware Multi-Interest Graph Neural Network for Session-based Recommendation' abstract: 'Session-based recommendation (SBR) is a challenging task, which aims at recommending next items based on anonymous interaction sequences. Despite the superior performance of existing methods for SBR, there are still several limitations: (i) Almost all existing works concentrate on single interest extraction and fail to disentangle multiple interests of user, which easily results in suboptimal representations for SBR. (ii) Furthermore, previous methods also ignore the multi-form temporal information, which is significant signal to obtain current intention for SBR. To address the limitations mentioned above, we propose a novel method, called Temporal aware Multi-Interest Graph Neural Network (TMI-GNN) to disentangle multi-interest and yield refined intention representations with the injection of two level temporal information. Specifically, by appending multiple interest nodes, we construct a multi-interest graph for current session, and adopt the GNNs to model the item-item relation to capture adjacent item transitions, item-interest relation to disentangle the multi-interests, and interest-item relation to refine the item representation. Meanwhile, we incorporate item-level time interval signals to guide the item information propagation, and interest-level time distribution information to assist the scattering of interest information. Experiments on three benchmark datasets demonstrate that TMI-GNN outperforms other state-of-the-art methods consistently.' volume: 189 URL: https://proceedings.mlr.press/v189/shen23a.html PDF: https://proceedings.mlr.press/v189/shen23a/shen23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-shen23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Qi family: Shen - given: Shixuan family: Zhu - given: Yitong family: Pang - given: Yiming family: Zhang - given: Zhihua family: Wei editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: id: shen23a issued: date-parts: - 2023 - 4 - 13 published: 2023-04-13 00:00:00 +0000 - title: 'Nighttime Semantic Segmentation with Unsupervised Learning and Cross Attention' abstract: 'In recent years, semantic segmentation has shown very good performance in daytime scenes. But in nighttime scenes, semantic segmentation greatly reduces its accuracy. Due to the lack of large-scale nighttime semantic segmentation datasets, it is difficult to directly train segmentation models for nighttime scenes. Therefore, it becomes important to adapt the daytime scene segmentation model to the nighttime scene without directly using the nighttime scene segmentation dataset. In this paper, we propose a framework based on unsupervised learning and cross attention. The proposed method fuses supervised daytime scenes and unsupervised nighttime scenes, the supervision information in the daytime scene and the texture information specific to the nighttime scene are fully utilized, and the model is adapted to both the daytime scene and the nighttime scene. Consistency regulation is used to make segmentation model adapt to the complex and changeable night scene texture and illumination. In view of the coarse correspondence of static objects between day and night image pairs in the Dark Zurich dataset, cross attention is proposed to make the model pay more attention to the parts of the night scene which are similar to the daytime scene. Extensive experiments on Dark Zurich and Nighttime Driving datasets show that our method obtains better performance in nighttime semantic segmentation.' volume: 189 URL: https://proceedings.mlr.press/v189/cheng23a.html PDF: https://proceedings.mlr.press/v189/cheng23a/cheng23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-cheng23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Jian family: Cheng - given: Yang-Feng family: Hu - given: Yu family: Dai - given: Xue family: Qiao - given: Li family: Yao - given: Jun-Yan family: Yang editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: id: cheng23a issued: date-parts: - 2023 - 4 - 13 published: 2023-04-13 00:00:00 +0000 - title: 'When to Classify Events in Open Times Series?' abstract: 'In numerous applications, for instance in predictive maintenance, there is a pression to predict events ahead of time with as much accuracy as possible while not delaying the decision unduly. This translates in the optimization of a trade-off between earliness and accuracy of the decisions, that has been the subject of research for time series of finite length and with a unique label. And this has led to powerful algorithms for Early Classification of Time Series (ECTS). This paper, for the first time, investigates such a trade-off when events of different classes occur in a streaming fashion, with no predefined end. In the Early Classification in Open Time Series problem (ECOTS), the task is to predict events, i.e. their class and time interval, at the moment that optimizes the accuracy vs. earliness trade-off. Interestingly, we find that ECTS algorithms can be sensibly adapted in a principled way to this new problem. We illustrate our methodology by transforming two state-of-the-art ECTS algorithms for the ECOTS scenario.Among the wide variety of applications that this new approach opens up, we develop here a predictive maintenance use case that optimizes alarm triggering times, thus demonstrating the power of this new approach. ' volume: 189 URL: https://proceedings.mlr.press/v189/achenchabe23a.html PDF: https://proceedings.mlr.press/v189/achenchabe23a/achenchabe23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-achenchabe23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Youssef family: Achenchabe - given: Alexis family: Bondu - given: Cornuéjols family: Antoine - given: Lemaire family: Vincent editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1-16 id: achenchabe23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1 lastpage: 16 published: 2023-04-13 00:00:00 +0000 - title: 'Graph annotation generative adversarial networks' abstract: 'We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features. We follow the strategy of implicit distribution modelling via generative adversarial network (GAN) combined with permutation equivariant message passing architecture operating over the sets of nodes and edges. This enables generating the feature vectors of all the graph objects in one go (in 2 phases) as opposed to a much slower one-by-one generations of sequential models, prevents the need for expensive graph matching procedures usually needed for likelihood-based generative models, and uses efficiently the network capacity by being insensitive to the particular node ordering in the graph representation. To the best of our knowledge, this is the first method that models the feature distribution along the graph skeleton allowing for generations of annotated graphs with user specified structures. Our experiments demonstrate the ability of our model to learn complex structured distributions through quantitative evaluation over three annotated graph datasets.' volume: 189 URL: https://proceedings.mlr.press/v189/boget23a.html PDF: https://proceedings.mlr.press/v189/boget23a/boget23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-boget23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Yoann family: Boget - given: Magda family: Gregorova - given: Alexandros family: Kalousis editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 16-16 id: boget23a issued: date-parts: - 2023 - 4 - 13 firstpage: 16 lastpage: 16 published: 2023-04-13 00:00:00 +0000 - title: 'Bayesian Change-Point Detection for Bandit Feedback in Non-stationary Environments' abstract: 'The stochastic multi-armed bandit problem has been widely studied under the stationary assumption. However in real world problems and industrial applications, this assumption is often unrealistic because the distributions of rewards may change over time. In this paper, we consider the piece-wise iid non-stationary stochastic multi-armed bandit problem with unknown change-points and we focus on the change of mean setup. To solve the latter, we propose a change-point based framework where we study a class of change-detection based optimal bandit policies that actively detects change-point using the restarted Bayesian online change-point detector and then restarts the bandit indices. Analytically, in the context of regret minimization, our proposal achieves a $\mathcal{O}(\sqrt{A T K_T })$ regret upper-bound where $K_T$ is the overall number of change-points up to the horizon $T$ and $A$ is the number of arms. The derived bound matches the existing lower bound for abruptly changing environments. Finally, we demonstrate the cumulative regret reduction of the our proposal over synthetic Bernoulli rewards as well as Yahoo! datasets of webpage click-through rates.' volume: 189 URL: https://proceedings.mlr.press/v189/alami23a.html PDF: https://proceedings.mlr.press/v189/alami23a/alami23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-alami23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Reda family: Alami editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 17-31 id: alami23a issued: date-parts: - 2023 - 4 - 13 firstpage: 17 lastpage: 31 published: 2023-04-13 00:00:00 +0000 - title: 'Out of Distribution Detection via Neural Network Anchoring' abstract: 'Our goal in this paper is to exploit heteroscedastic temperature scaling as a calibration strategy for out of distribution (OOD) detection. Heteroscedasticity here refers to the fact that the optimal temperature parameter for each sample can be different, as opposed to conventional approaches that use the same value for the entire distribution. To enable this, we propose a new training strategy called anchoring that can estimate appropriate temperature values for each sample, leading to state-of-the-art OOD detection performance across several benchmarks. Using NTK theory, we show that this temperature function estimate is closely linked to the epistemic uncertainty of the classifier, which explains its behavior. In contrast to some of the best-performing OOD detection approaches, our method does not require exposure to additional outlier datasets, custom calibration objectives, or model ensembling. Through empirical studies with different OOD detection settings – far OOD, near OOD, and semantically coherent OOD - we establish a highly effective OOD detection approach.' volume: 189 URL: https://proceedings.mlr.press/v189/anirudh23a.html PDF: https://proceedings.mlr.press/v189/anirudh23a/anirudh23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-anirudh23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Rushil family: Anirudh - given: Jayaraman J. family: Thiagarajan editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 32-47 id: anirudh23a issued: date-parts: - 2023 - 4 - 13 firstpage: 32 lastpage: 47 published: 2023-04-13 00:00:00 +0000 - title: 'On the Episodic Difficulty of Few-shot Learning' abstract: 'Dog vs. hot dog and dog vs. wolf, which one tends to be a harder comparison task? While simple, this question can be meaningful for few-shot classification. Few-shot learning enables trained models to recognize unseen classes through just a few labelled samples. As such, trained few-shot models usually have to possess the ability to assess the similarity degree between the unlabelled and labelled samples. In each few-shot learning episode, a combination of the labelled support set and unlabelled query set are sampled from the training dataset for model-training. In the episodic settings of few-shot learning, most algorithms draw the data samples uniformly at random for training. However, this approach disregards concepts of difficulty of each training episode, which may make a difference. After all, it is usually easier to differentiate between a dog and a hot dog, versus the dog and a wolf. Therefore, in this paper, we delve into the concept of episodic difficulty, or difficulty of each training episode, discovering several insights and proposing strategies to utilize the difficulty. Firstly, defining episodic difficulty as a training loss, we find and study the correlation between episodic difficulty and visual similarity among data samples in each episode. Secondly, we assess the respective usefulness of easy and difficult episodes for the training process. Lastly, based on the assessment, we design a curriculum for few-shot learning to support training with incremental difficulty. We observe that such an approach can achieve faster convergence for few-shot algorithms, reducing the average training time by around 50%. It can also make meta-learning algorithms achieve an increase in final testing accuracy scores.' volume: 189 URL: https://proceedings.mlr.press/v189/bai23a.html PDF: https://proceedings.mlr.press/v189/bai23a/bai23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-bai23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Yunwei family: Bai - given: Zhenfeng family: He - given: Junfeng family: Hu editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 48-63 id: bai23a issued: date-parts: - 2023 - 4 - 13 firstpage: 48 lastpage: 63 published: 2023-04-13 00:00:00 +0000 - title: 'Learning with Domain Knowledge to Develop Justifiable Convolutional Networks' abstract: 'The inherent structure of the Convolutional Neural Networks (CNN) allows them to extract features that are highly correlated with the classes while performing image classification. However, it may happen that the extracted features are merely coincidental and may not be justifiable from a human perspective. For example, from a set of images of cows on grassland, CNN can erroneously extract grass as the feature of the class cow. There are two main limitations to this kind of learning: firstly, in many false-negative cases, correct features will not be used, and secondly, in false-positive cases the system will lack accountability. There is no implicit way to inform CNN to learn the features that are justifiable from a human perspective to resolve these issues. In this paper, we argue that if we provide domain knowledge to guide the learning process of CNN, it is possible to reliably learn the justifiable features. We propose a systematic yet simple mechanism to incorporate domain knowledge to guide the learning process of the CNNs to extract justifiable features. The flip side is that it needs additional input. However, we have shown that even with minimal additional input our method can effectively propagate the knowledge within a class during training. We demonstrate that justifiable features not only enhance accuracy but also demand less amount of data and training time. Moreover, we also show that the proposed method is more robust against perturbational changes in the input images.' volume: 189 URL: https://proceedings.mlr.press/v189/bhosale23a.html PDF: https://proceedings.mlr.press/v189/bhosale23a/bhosale23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-bhosale23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Rimmon family: Bhosale - given: Mrinal family: Das editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 64-79 id: bhosale23a issued: date-parts: - 2023 - 4 - 13 firstpage: 64 lastpage: 79 published: 2023-04-13 00:00:00 +0000 - title: 'Robust Multi-Objective Reinforcement Learning with Dynamic Preferences' abstract: 'This paper considers multi-objective reinforcement learning (MORL) when preferences over the multiple tasks are not perfectly known. Indeed, it is often the case in practice that an agent is trying to achieve tasks that may have competing goals but does not exactly know how to trade them off. The goal of MORL is thus to learn optimal policies under a set of possible preferences leading to different trade-offs on the Pareto frontier. Here, we propose a new method by considering the dynamics of preferences over tasks. While this is a more realistic setup in many scenarios, more importantly, it helps us devise a simple and straightforward approach by considering a surrogate state space made up of both states and preferences, which leads to a joint exploration of states and preferences. Static (and possibly unknown) preferences can also be understood as a limiting case of our framework. In sum, this allows us to devise both deep Q-learning and actor-critic methods based on planning under a preference-dependent policy and learning the multi-dimensional value function under said policy. Finally, the performance and effectiveness of our method are demonstrated in experiments run on different domains.' volume: 189 URL: https://proceedings.mlr.press/v189/buet-golfouse23a.html PDF: https://proceedings.mlr.press/v189/buet-golfouse23a/buet-golfouse23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-buet-golfouse23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Francois family: Buet-Golfouse - given: Parth family: Pahwa editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 96-111 id: buet-golfouse23a issued: date-parts: - 2023 - 4 - 13 firstpage: 96 lastpage: 111 published: 2023-04-13 00:00:00 +0000 - title: 'Fairness Trade-Offs and Partial Debiasing' abstract: 'Previous literature has shown that bias mitigating algorithms were sometimes prone to overfitting and had poor out-of-sample generalisation. This paper is first and foremost concerned with establishing a mathematical framework to tackle the specific issue of generalisation. Throughout this work, we consider fairness trade-offs and objectives mixing statistical loss over the whole sample and fairness penalties on categories (which could stem from different values of protected attributes), encompassing partial de-biasing. We do so by adopting two different but complementary viewpoints: first, we consider a PAC-type setup and derive probabilistic upper bounds involving sample-only information; second, we leverage an asymptotic framework to derive a closed-form limiting distribution for the difference between the empirical trade-off and the true trade-off. While these results provide guarantees for learning fairness metrics across categories, they also point out to the key (but asymmetric) role played by class imbalance. To summarise, learning fairness without having access to enough category-level samples is hard, and a simple numerical experiment shows that it can lead to spurious results.' volume: 189 URL: https://proceedings.mlr.press/v189/buet-golfouse23b.html PDF: https://proceedings.mlr.press/v189/buet-golfouse23b/buet-golfouse23b.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-buet-golfouse23b.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Francois family: Buet-Golfouse - given: Islam family: Utyagulov editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 112-136 id: buet-golfouse23b issued: date-parts: - 2023 - 4 - 13 firstpage: 112 lastpage: 136 published: 2023-04-13 00:00:00 +0000 - title: 'Robust Scene Text Detection via Learnable Scene Transformations' abstract: 'Scene text detection based on deep neural networks has been extensively studied in the last few years. However, the task of detecting texts in complex scenes such as bad weather and image distortions has not received sufficient attentions in existing works, which is crucial for real-world applications such as text translation, autonomous driving, etc. In this paper, we propose a novel strategy to automatically search for the effective scene transformation polices to augment images in the training phase. In addition, we build a new dataset, Robust-Text, to evaluate the robustness of text detection methods in real complex scenes. Experiments conducted on the ICDAR2015, MSRA-TD500 and Robust-Text datasets demonstrate that our method can effectively improve the robustness of text detectors in complex scenes.' volume: 189 URL: https://proceedings.mlr.press/v189/cao23a.html PDF: https://proceedings.mlr.press/v189/cao23a/cao23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-cao23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Yuheng family: Cao - given: Mengjie family: Zhou - given: Jie family: Chen editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 137-152 id: cao23a issued: date-parts: - 2023 - 4 - 13 firstpage: 137 lastpage: 152 published: 2023-04-13 00:00:00 +0000 - title: 'A two-stream convolution architecture for ESC based on audio feature distanglement' abstract: ' ESC (Environmental Sound Classification) is an active area of research in the field of audio classification that has made significant progress in recent years. The current mainstream ESC methods are based on increasing the dimension of the extracted audio features and therefore draw on the two-dimensional convolution methods used in image processing. However, two-dimensional convolution is expensive to train and the complexity of the corresponding model is usually very high. In response to these issues, we propose a novel two-stream neural network model by the idea of disentanglement, which uses onedimensional convolution for feature extraction to disentangle the audio features into the time and frequency domains separately. Our approach balances computational pressure with classification accuracy well. The accuracy of our approach on the Urbansound 8k and Esc-10 datasets was 98.51% and 97.50%, respectively, which exceeds that of most models. Meanwhile, the model complexity is also lower.' volume: 189 URL: https://proceedings.mlr.press/v189/chang23a.html PDF: https://proceedings.mlr.press/v189/chang23a/chang23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-chang23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Zhenghao family: Chang - given: Ruhan family: He - given: Yongsheng family: Yu - given: Zili family: Zhang - given: GeLi family: Bai editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 153-168 id: chang23a issued: date-parts: - 2023 - 4 - 13 firstpage: 153 lastpage: 168 published: 2023-04-13 00:00:00 +0000 - title: 'ProtoBandit: Efficient Prototype Selection via Multi-Armed Bandits' abstract: 'In this work, we propose a multi-armed bandit based framework for identifying a compact set of informative data instances (i.e., the prototypes) that best represents a given target set. Prototypical examples of a given dataset offer interpretable insights into the underlying data distribution and assist in example-based reasoning, thereby influencing every sphere of human decision making. A key challenge is the large-scale setting, in which similarity comparison between pairs of data points needs to be done for almost all possible pairs. We propose to overcome this limitation by employing stochastic greedy search on the space of prototypical examples and multi-armed bandit approach for reducing the number of similarity comparisons. A salient feature of the proposed approach is that the total number of similarity comparisons needed is independent of the size of the target set. Empirically, we observe that our proposed approach, ProtoBandit, reduces the total number of similarity computation calls by several orders of magnitudes (100-1000 times) while obtaining solutions similar in quality to those from existing state-of-the-art approaches.' volume: 189 URL: https://proceedings.mlr.press/v189/chaudhuri23a.html PDF: https://proceedings.mlr.press/v189/chaudhuri23a/chaudhuri23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-chaudhuri23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Arghya Roy family: Chaudhuri - given: Pratik family: Jawanpuria - given: Bamdev family: Mishra editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 169-184 id: chaudhuri23a issued: date-parts: - 2023 - 4 - 13 firstpage: 169 lastpage: 184 published: 2023-04-13 00:00:00 +0000 - title: 'Balanced Spatial-Temporal Graph Structure Learning for Multivariate Time Series Forecasting: A Trade-off between Efficiency and Flexibility' abstract: 'Accurate forecasting of multivariate time series is an extensively studied subject in finance, transportation, and computer science. Fully mining the correlation and causation between the variables in a multivariate time series exhibits noticeable results in improving the performance of a time series model. Recently, some models have explored the dependencies between variables through end-to-end graph structure learning without the need for predefined graphs. However, current models do not incorporate the trade-off between efficiency and flexibility and make insufficient use of the information contained in time series in the design of graph structure learning algorithms. This paper alleviates the above issues by proposing Balanced Graph Structure Learning for Forecasting (BGSLF), a novel and effective deep learning model that joins graph structure learning and forecasting. Technically, BGSLF leverages the spatial information into convolutional operations and extracts temporal dynamics using the diffusion convolutional recurrent network. The proposed framework emphasizes the trade-off between efficiency and flexibility by introducing Multi-Graph Generation Network (MGN) and Graph Selection Module. In addition, a method named Smooth Sparse Unit (SSU) is designed to sparse the learned graph structures, which conforms to the sparse spatial correlations in the real world. Extensive experiments on four real-world datasets demonstrate that our model achieves state-of-the-art performances with minor trainable parameters. Our code is publicly available at https://github.com/onceCWJ/BGSLF.' volume: 189 URL: https://proceedings.mlr.press/v189/chen23a.html PDF: https://proceedings.mlr.press/v189/chen23a/chen23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-chen23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Weijun family: Chen - given: Yanze family: Wang - given: Chengshuo family: Du - given: Zhenglong family: Jia - given: Feng family: Liu - given: Ran family: Chen editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 185-200 id: chen23a issued: date-parts: - 2023 - 4 - 13 firstpage: 185 lastpage: 200 published: 2023-04-13 00:00:00 +0000 - title: 'Noisy Riemannian Gradient Descent for Eigenvalue Computation with Application to Inexact Stochastic Recursive Gradient Algorithm' abstract: 'We provide a robust convergence analysis of the Riemannian gradient descent algorithm for computing the leading eigenvector of a real symmetric matrix. Our result characterizes the convergence behavior of the algorithm under the noisy updates, where noises can be generated by a stochastic process or could be chosen adversarially. The noisy Riemannian gradient descent has a broad range of applications in machine learning and statistics, e.g., streaming principal component analysis or privacy-preserving spectral analysis. In particular, we demonstrate the usefulness of our convergence bound with a new eigengap-dependent sample complexity of the inexact Riemannian stochastic recursive gradient algorithm, which utilizes mini-batch gradients instead of full gradients in outer loops. Our robust convergence paradigm strictly improves the state-of-the-art sample complexity in terms of the gap dependence.' volume: 189 URL: https://proceedings.mlr.press/v189/chen23c.html PDF: https://proceedings.mlr.press/v189/chen23c/chen23c.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-chen23c.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: You-Lin family: Chen - given: Zhiqiang family: Xu - given: Ping family: Li editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 201-216 id: chen23c issued: date-parts: - 2023 - 4 - 13 firstpage: 201 lastpage: 216 published: 2023-04-13 00:00:00 +0000 - title: 'On the Convergence of Decentralized Adaptive Gradient Methods' abstract: 'Adaptive gradient methods including Adam, AdaGrad, and their variants have been very successful for training deep learning models, such as neural networks. Meanwhile, given the need for distributed computing, distributed optimization algorithms are rapidly becoming a focal point. With the growth of computing power and the need for using machine learning models on mobile devices, the communication cost of distributed training algorithms needs careful consideration. In this paper, we introduce novel convergent decentralized adaptive gradient methods and rigorously incorporate adaptive gradient methods into decentralized training procedures. Specifically, we propose a general algorithmic framework that can convert existing adaptive gradient methods to their decentralized counterparts. In addition, we thoroughly analyze the convergence behavior of the proposed algorithmic framework and show that if a given adaptive gradient method converges, under some specific conditions, then its decentralized counterpart is also convergent. We illustrate the benefit of our generic decentralized framework on prototype methods, AMSGrad and AdaGrad.' volume: 189 URL: https://proceedings.mlr.press/v189/chen23b.html PDF: https://proceedings.mlr.press/v189/chen23b/chen23b.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-chen23b.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Xiangyi family: Chen - given: Belhal family: Karimi - given: Weijie family: Zhao - given: Ping family: Li editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 217-232 id: chen23b issued: date-parts: - 2023 - 4 - 13 firstpage: 217 lastpage: 232 published: 2023-04-13 00:00:00 +0000 - title: 'Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning' abstract: 'We consider the regret minimization problem in reinforcement learning (RL) in the episodic setting. In many real-world RL environments, the state and action spaces are continuous or very large. Existing approaches establish regret guarantees by either a low-dimensional representation of the stochastic transition model or an approximation of the $Q$-functions. However, the understanding of function approximation schemes for state-value functions largely remains missing. In this paper, we propose an online model-based RL algorithm, namely the CME-RL, that learns embeddings of the state-transition distribution in a reproducing kernel Hilbert space while carefully balancing the exploitation-exploration tradeoff. We demonstrate the efficiency of our algorithm by proving a frequentist (worst-case) regret bound that is of order $\tilde{O}\big(H\gamma_N\sqrt{N}\big)$\footnote{ $\tilde{O}(\cdot)$ hides only absolute constant and poly-logarithmic factors.}, where $H$ is the episode length, $N$ is the total number of time steps and $\gamma_N$ is an information theoretic quantity relating the effective dimension of the state-action feature space. Our method bypasses the need for estimating transition probabilities and applies to any domain on which kernels can be defined. It also brings new insights into the general theory of kernel methods for approximate inference and RL regret minimization.' volume: 189 URL: https://proceedings.mlr.press/v189/chowdhury23a.html PDF: https://proceedings.mlr.press/v189/chowdhury23a/chowdhury23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-chowdhury23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Sayak Ray family: Chowdhury - given: Rafael family: Oliveira editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 249-264 id: chowdhury23a issued: date-parts: - 2023 - 4 - 13 firstpage: 249 lastpage: 264 published: 2023-04-13 00:00:00 +0000 - title: 'Multiple Imputation with Neural Network Gaussian Process for High-dimensional Incomplete Data' abstract: 'Missing data are ubiquitous in real world applications and, if not adequately handled, may lead to the loss of information and biased findings in downstream analysis. Particularly, high-dimensional incomplete data with a moderate sample size, such as analysis of multi-omics data, present daunting challenges. Imputation is arguably the most popular method for handling missing data, though existing imputation methods have a number of limitations. Single imputation methods such as matrix completion methods do not adequately account for imputation uncertainty and hence would yield improper statistical inference. In contrast, multiple imputation (MI) methods allow for proper inference but existing methods do not perform well in high-dimensional settings. Our work aims to address these significant methodological gaps, leveraging recent advances in neural network Gaussian process (NNGP) from a Bayesian viewpoint. We propose two NNGP-based MI methods, namely MI-NNGP, that can apply multiple imputations for missing values from a joint (posterior predictive) distribution. The MI-NNGP methods are shown to significantly outperform existing state-of-the-art methods on synthetic and real datasets, in terms of imputation error, statistical inference, robustness to missing rates, and computation costs, under three missing data mechanisms, MCAR, MAR, and MNAR.' volume: 189 URL: https://proceedings.mlr.press/v189/dai23a.html PDF: https://proceedings.mlr.press/v189/dai23a/dai23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-dai23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Zongyu family: Dai - given: Zhiqi family: Bu - given: Qi family: Long editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 265-279 id: dai23a issued: date-parts: - 2023 - 4 - 13 firstpage: 265 lastpage: 279 published: 2023-04-13 00:00:00 +0000 - title: 'BayesAdapter: Being Bayesian, Inexpensively and Reliably, via Bayesian Fine-tuning' abstract: 'Despite their theoretical appealingness, Bayesian neural networks (BNNs) are left behind in real-world adoption, mainly due to persistent concerns on their scalability, accessibility, and reliability. In this work, we develop the BayesAdapter framework to relieve these concerns. In particular, we propose to adapt pre-trained deterministic NNs to be variational BNNs via cost-effective Bayesian fine-tuning. Technically, we develop a modularized implementation for the learning of variational BNNs, and refurbish the generally applicable exemplar reparameterization trick through exemplar parallelization to efficiently reduce the gradient variance in stochastic variational inference. Based on the the lightweight Bayesian learning paradigm, we conduct extensive experiments on a variety of benchmarks, and show that our method can consistently induce posteriors with higher quality than competitive baselines, yet significantly reducing training overheads.' volume: 189 URL: https://proceedings.mlr.press/v189/deng23b.html PDF: https://proceedings.mlr.press/v189/deng23b/deng23b.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-deng23b.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Zhijie family: Deng - given: Jun family: Zhu editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 280-295 id: deng23b issued: date-parts: - 2023 - 4 - 13 firstpage: 280 lastpage: 295 published: 2023-04-13 00:00:00 +0000 - title: 'A Self-improving Skin Lesions Diagnosis Framework Via Pseudo-labeling and Self-distillation' abstract: 'In the past few years, supervised-based deep learning methods has yielded good results in skin lesions diagnosis tasks. Unfortunately, obtaining large of labels for medical images is expensive and time consuming. In this paper, we propose a self-improving skin lesions diagnosis (SISLD) framework to explore useful information in unlabeled data. We first propose a semi-supervised model ${f}$, which combining consistency and class-balanced pseudo-labeling to make full use of unlabeled data in scenarios with sparse manually labeled samples, and obtain a teacher model ${f_{t}}$ by semi-supervised self-training. Then, we introduce self-distillation method to enable knowledge distillation for the diagnosis of skin lesions. Finally, we measure diagnostic effectiveness in the context of label sparsity and class imbalance. The experiments on skin lesion images dataset ISIC2018 shows that SISLD achieves significant improvements in AUC, Accuracy, Specificity and Sensitivity.' volume: 189 URL: https://proceedings.mlr.press/v189/deng23a.html PDF: https://proceedings.mlr.press/v189/deng23a/deng23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-deng23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Shaochang family: Deng - given: Mengxiao family: Yin - given: Feng family: Yang editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 296-310 id: deng23a issued: date-parts: - 2023 - 4 - 13 firstpage: 296 lastpage: 310 published: 2023-04-13 00:00:00 +0000 - title: 'Kernelized multi-graph matching' abstract: 'Multigraph matching is a recent variant of the graph matching problem. In this framework, the optimization procedure considers several graphs and enforces the consistency of the matches along the graphs. This constraint can be formalized as a cycle consistency across the pairwise permutation matrices, which implies the definition of a universe of vertex (Pachauri et al., 2013). The label of each vertex is encoded by a sparse vector and the dimension of this space corresponds to the rank of the bulk permutation matrix, the matrix built from the aggregation of all the pairwise permutation matrices. The matching problem can then be formulated as a non-convex quadratic optimization problem (QAP) under constraints imposed on the rank and the permutations. In this paper, we introduce a novel kernelized multigraph matching technique that handles vectors of attributes on both the vertices and edges of the graphs, while maintaining a low memory usage. We solve the QAP problem using a projected power optimization approach and propose several projectors leading to improved stability of the results. We provide several experiments showingthat our method is competitive against other unsupervised methods.' volume: 189 URL: https://proceedings.mlr.press/v189/dupe23a.html PDF: https://proceedings.mlr.press/v189/dupe23a/dupe23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-dupe23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: François-Xavier family: Dupé - given: Rohit family: Yadav - given: Guillaume family: Auzias - given: Sylvain family: Takerkart editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 311-326 id: dupe23a issued: date-parts: - 2023 - 4 - 13 firstpage: 311 lastpage: 326 published: 2023-04-13 00:00:00 +0000 - title: 'Towards Data-Free Domain Generalization' abstract: 'In this work, we investigate the unexplored intersection of domain generalization (DG) and data-free learning. In particular, we address the question: How can knowledge contained in models trained on different source domains be merged into a single model that generalizes well to unseen target domains, in the absence of source and target domain data? Machine learning models that can cope with domain shift are essential for real-world scenarios with often changing data distributions. Prior DG methods typically rely on using source domain data, making them unsuitable for private decentralized data. We define the novel problem of Data-Free Domain Generalization (DFDG), a practical setting where models trained on the source domains separately are available instead of the original datasets, and investigate how to effectively solve the domain generalization problem in that case. We propose DEKAN, an approach that extracts and fuses domain-specific knowledge from the available teacher models into a student model robust to domain shift. Our empirical evaluation demonstrates the effectiveness of our method which achieves first state-of-the-art results in DFDG by significantly outperforming data-free knowledge distillation and ensemble baselines.' volume: 189 URL: https://proceedings.mlr.press/v189/frikha23a.html PDF: https://proceedings.mlr.press/v189/frikha23a/frikha23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-frikha23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Ahmed family: Frikha - given: Haokun family: Chen - given: Denis family: Krompaß - given: Thomas family: Runkler - given: Volker family: Tresp editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 327-342 id: frikha23a issued: date-parts: - 2023 - 4 - 13 firstpage: 327 lastpage: 342 published: 2023-04-13 00:00:00 +0000 - title: 'Trusted Loss Correction for Noisy Multi-Label Learning' abstract: 'Noisy and corrupted labels are shown to significantly undermine the performance of multi-label learning, which has multiple labels in each image. Correcting the loss via a label corruption matrix is effective in improving the robustness of single-label classification against noisy labels. However, estimating the corruption matrix for multi-label problems is no mean feat due to the unbalanced distributions of labels and the presence of multiple objects that may be mapped into the same labels. In this paper, we propose a robust multi-label classifier against label noise, TLCM, which corrects the loss based on a corruption matrix estimated on trusted data. To overcome the challenge of unbalanced label distribution and multi-object mapping, we use trusted single-label data as regulators to correct the multi-label corruption matrix. Empirical evaluation on real-world vision and object detection datasets, i.e., MS-COCO, NUS-WIDE, and MIRFLICKR, shows that our method under medium (30%) and high (60%) corruption levels outperforms state-of-the-art multi-label classifier (ASL) and noise-resilient multi-label classifier (MPVAE), by on average 12.5% and 26.3% mean average precision (mAP) points, respectively.' volume: 189 URL: https://proceedings.mlr.press/v189/ghiassi23a.html PDF: https://proceedings.mlr.press/v189/ghiassi23a/ghiassi23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-ghiassi23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Amirmasoud family: Ghiassi - given: Cosmin Octavian family: Pene - given: Robert family: Birke - given: Lydia.Y family: Chen editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 343-358 id: ghiassi23a issued: date-parts: - 2023 - 4 - 13 firstpage: 343 lastpage: 358 published: 2023-04-13 00:00:00 +0000 - title: 'Multi Label Loss Correction against Missing and Corrupted Labels' abstract: 'Missing and corrupted labels can significantly ruin the learning process and, consequently, the classifier performance. Multi-label learning where each instance is tagged with variable number of labels is particularly affected. Although missing labels (false-negatives) is a well-studied problem in multi-label learning, it is considerably more challenging to have both false-negatives (missing labels) and false-positives (corrupted labels) simultaneously in multi-label datasets. In this paper, we propose Multi-Label Loss with Self Correction (MLLSC) which is a loss robust against coincident missing and corrupted labels. MLLSC computes the loss based on the true-positive (true-negative) or false-positive (false-negative) labels and deep neural network expertise. To distinguish between false-positive (false-negative) and true-positive (true-negative) labels, we use the output probability of the deep neural network during the learning process. Our method As MLLSC can be combined with different types of multi-label loss functions, we also address the label imbalance problem of multi-label datasets. Empirical evaluation on real-world vision datasets, i.e., MS-COCO, and MIR-FLICKR, shows that our method under medium (0.3) and high (0.6) corrupted and missing label probabilities outperform the state-of-the-art methods by, on average 23.97% and 9.31% mean average precision (mAP) points, respectively.' volume: 189 URL: https://proceedings.mlr.press/v189/ghiassi23b.html PDF: https://proceedings.mlr.press/v189/ghiassi23b/ghiassi23b.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-ghiassi23b.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Amirmasoud family: Ghiassi - given: Robert family: Birke - given: Lydia.Y family: Chen editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 359-374 id: ghiassi23b issued: date-parts: - 2023 - 4 - 13 firstpage: 359 lastpage: 374 published: 2023-04-13 00:00:00 +0000 - title: 'DALE: Differential Accumulated Local Effects for efficient and accurate global explanations' abstract: 'Accumulated Local Effect (ALE) is a method for accurately estimating feature effects, overcoming fundamental failure modes of previously-existed methods, such as Partial Dependence Plots. However, \textit{ALE’s approximation}, i.e. the method for estimating ALE from the limited samples of the training set, faces two weaknesses. First, it does not scale well in cases where the input has high dimensionality, and, second, it is vulnerable to out-of-distribution (OOD) sampling when the training set is relatively small. In this paper, we propose a novel ALE approximation, called Differential Accumulated Local Effects (DALE), which can be used in cases where the ML model is differentiable and an auto-differentiable framework is accessible. Our proposal has significant computational advantages, making feature effect estimation applicable to high-dimensional Machine Learning scenarios with near-zero computational overhead. Furthermore, DALE does not create artificial points for calculating the feature effect, resolving misleading estimations due to OOD sampling. Finally, we formally prove that, under some hypotheses, DALE is an unbiased estimator of ALE and we present a method for quantifying the standard error of the explanation. Experiments using both synthetic and real datasets demonstrate the value of the proposed approach.' volume: 189 URL: https://proceedings.mlr.press/v189/gkolemis23a.html PDF: https://proceedings.mlr.press/v189/gkolemis23a/gkolemis23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-gkolemis23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Vasilis family: Gkolemis - given: Theodore family: Dalamagas - given: Christos family: Diou editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 375-390 id: gkolemis23a issued: date-parts: - 2023 - 4 - 13 firstpage: 375 lastpage: 390 published: 2023-04-13 00:00:00 +0000 - title: 'Circulant-interactive Transformer with Dimension-aware Fusion for Multimodal Sentiment Analysis' abstract: 'Multimodal sentiment analysis (MSA) is gaining traction as a critical tool for understanding human behavior and enabling a wide range of applications. Since data of different modalities might lie in completely distinct spaces, it is very challenging to perform effective fusion and analysis from asynchronous multimodal streams. Most of previous works focused on aligned fusion, which is unpractical in real-world scenarios. The recent Multimodal Transformer (MulT) approach attends to model the correlations between elements from different modalities in an unaligned manner. However, it collects temporal information by self-attention transformer which is a sequence model, implying that interactions across distinct time steps are not sufficient. In this paper, we propose the Citculant-interactive Transformer Network with dimension-aware fusion (CITN-DAF), which enables parallel computation of different modalities among different time steps and alleviates inter-modal temporal sensitivity while preserving intra-modal semantic order. By incorporating circulant matrices into the cross-modal attention mechanism, CITN-DAF is aimed to examine all conceivable interactions between vectors of different modalities. In addition, a dimension-aware fusion method is presented, which projects feature representations into different subspaces for an in-depth fusion. We evaluate CITN-DAF on three commonly used sentiment analysis benchmarks including CMU-MOSEI, CMU-MOSI and IEMOCAP. Extensive experimental results reveal that CITN-DAF is superior in cross-modal semantic interactions and outperforms the state-of-the-art multimodal methods.' volume: 189 URL: https://proceedings.mlr.press/v189/gong23a.html PDF: https://proceedings.mlr.press/v189/gong23a/gong23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-gong23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Peizhu family: Gong - given: Jin family: Liu - given: Xiliang family: Zhang - given: Xingye family: Li - given: Zijun family: Yu editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 391-406 id: gong23a issued: date-parts: - 2023 - 4 - 13 firstpage: 391 lastpage: 406 published: 2023-04-13 00:00:00 +0000 - title: 'BeautifAI - Personalised Occasion-based Makeup Recommendation' abstract: 'With the global metamorphosis of the beauty industry and the rising demand for beauty products worldwide, the need for a robust makeup recommendation system has never been more. Despite the significant advancements made towards personalised makeup recommendation, the current research still falls short of incorporating the context of occasion and integrating feedback for users. In this work, we propose BeautifAI, a novel recommendation system, delivering personalised occasion-oriented makeup recommendations to users. The proposed work’s novel contributions, including incorporating occasion context to makeup recommendation and a region-wise method using neural embeddings, set our system apart from the current work in makeup recommendation. We also propose real-time makeup previews and continuous makeup feedback to provide a more personalised and interactive experience to users.' volume: 189 URL: https://proceedings.mlr.press/v189/gulati23a.html PDF: https://proceedings.mlr.press/v189/gulati23a/gulati23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-gulati23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Kshitij family: Gulati - given: Gaurav family: Verma - given: Mukesh family: Mohania - given: Ashish family: Kundu editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 407-419 id: gulati23a issued: date-parts: - 2023 - 4 - 13 firstpage: 407 lastpage: 419 published: 2023-04-13 00:00:00 +0000 - title: 'Position-dependent partial convolutions for supervised spatial interpolation' abstract: 'Acquiring continuous spatial data, e.g., spatial ground motion is essential to assess the damaged area and appropriately assign rescue and medical teams. To this purpose, spatial interpolation methods have been developed to estimate the value of unobserved points linearly from neighbor observed values, i.e., inverse distance weighting and Kriging. Recently, realistic spatial continuous environmental data with various scenarios can be generated by 3D finite difference methods with a high-resolution structure model. It enables us to collect supervised data even for unobserved points. Along this line, we propose a framework of supervised spatial interpolation and apply highly advanced deep inpainting methods where we treat spatially distributed observed points as a masked image and non-linearly expand them through convolutional encoder-decoder networks. However, the property of translation invariance would avoid locally fine-grained interpolation since the relation between the target and surrounding observation points varies over regions due to its topography and subsurface structure. To overcome this problem, we propose introducing position-dependent convolution where kernel weights are adjusted depending on their position on an image based on the trainable position-feature map. We show the effectiveness of our proposed method, called, PoDIM (Position-dependent Deep Inpainting Method), through experiments using simulated ground-motion data.' volume: 189 URL: https://proceedings.mlr.press/v189/hachiya23a.html PDF: https://proceedings.mlr.press/v189/hachiya23a/hachiya23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-hachiya23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Hirotaka family: Hachiya - given: Kotaro family: Nagayoshi - given: Asako family: Iwaki - given: Takahiro family: Maeda - given: Naonori family: Ueda - given: Hiroyuki family: Fujiwara editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 420-435 id: hachiya23a issued: date-parts: - 2023 - 4 - 13 firstpage: 420 lastpage: 435 published: 2023-04-13 00:00:00 +0000 - title: 'SNAIL: Semi-Separated Uncertainty Adversarial Learning for Universal Domain Adaptation' abstract: ' Universal domain adaptation (UniDA) is a new sub-topic of unsupervised domain adaptation. It handles the problem that the source or target domain possibly has open-class samples. The inborn challenge is to detect the open-class samples in the test phase. Pioneering studies could be viewed as dependent-detector-based methods. They cleverly design efficient uncertainty metrics (\eg, confidence, entropy, distance) based on the outputs of domain adaptation models (predictor) to detect open-class samples. However, they have a pain point in setting extremely-sensitive and task-dependent thresholds on the uncertainty metrics to filter open-class samples. To bypass this pain point, we propose a semi-separated-detector-based method, Semi-Separated Uncertainty Adversarial Learning (SNAIL). We build a semi-separated uncertainty decision-maker to enable sensitive-threshold-free detection. It receives multiple uncertainty metrics as attributes and separately learns the thresholds of uncertainty metrics in a multi-level decision rule. For some challenging tasks, the uncertainty margins between common and open classes are subtle, leading to difficulty learning optimal decision rules. We present the uncertainty separation loss to enlarge the uncertainty margin. Further, forcibly aligning the distributions could incorrectly align the open classes to common classes. Thanks to the open-class detection strategy, we design the conditional-weighted adversarial loss that adversarially and selectively matches the feature distributions to defeat the distribution misalignment problem. Extensive experiments show that SNAIL remarkably outperforms the state-of-the-art domain adaptation methods, with over 25% improvements in open-class detection accuracy for some tasks.' volume: 189 URL: https://proceedings.mlr.press/v189/han23a.html PDF: https://proceedings.mlr.press/v189/han23a/han23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-han23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Zhongyi family: Han - given: Wan family: Su - given: Rundong family: He - given: Yilong family: Yin editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 436-451 id: han23a issued: date-parts: - 2023 - 4 - 13 firstpage: 436 lastpage: 451 published: 2023-04-13 00:00:00 +0000 - title: 'A Novel Graph Aggregation Method Based on Feature Distribution Around Each Ego-node for Heterophily' abstract: 'In this paper, we propose a novel graph aggregation method based on feature distribution around each ego-node (a node to which features are aggregated) for heterophily. In heterophily graphs, labels of neighboring nodes can be uniformly distributed. In such case, aggregated features by existing GNNs will be always similar regardless of the label of ego-node and fail to capture useful information for a node classification task. Since the existing methods basically ignore label distribution around the ego-node, we attempt to handle heterophily graphs through dynamic aggregations so that nodes with similar vicinity characteristics exhibit similar behavior. In particular, we adjust the amount of aggregation based on the features generated by higher-order neighbors, since they reflect the label distribution around each ego-node. By doing this, we can take the influence of distant nodes into account while adapting local structures of each node. Extensive experiments demonstrate that the proposed method achieves higher performance in heterophily graphs by up to 14.68% compared with existing methods.' volume: 189 URL: https://proceedings.mlr.press/v189/haruta23a.html PDF: https://proceedings.mlr.press/v189/haruta23a/haruta23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-haruta23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Shuichiro family: Haruta - given: Tatsuya family: Konishi - given: Mori family: Kurokawa editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 452-466 id: haruta23a issued: date-parts: - 2023 - 4 - 13 firstpage: 452 lastpage: 466 published: 2023-04-13 00:00:00 +0000 - title: 'Learning Practical Communication Strategies in Cooperative Multi-Agent Reinforcement Learning' abstract: 'In Multi-Agent Reinforcement Learning, communication is critical to encourage cooperation among agents. Communication in realistic wireless networks can be highly unreliable due to network conditions varying with agents’ mobility, and stochasticity in the transmission process. We propose a framework to learn practical communication strategies by addressing three fundamental questions: (1) \emph{When}: Agents learn the timing of communication based on not only message importance but also wireless channel conditions. (2) \emph{What}: Agents augment message contents with wireless network measurements to better select the game and communication actions. (3) \emph{How}: Agents use a novel neural message encoder to preserve all information from received messages, regardless of the number and order of messages. Simulating standard benchmarks under realistic wireless network settings, we show significant improvements in game performance, convergence speed and communication efficiency compared with state-of-the-art.' volume: 189 URL: https://proceedings.mlr.press/v189/hu23a.html PDF: https://proceedings.mlr.press/v189/hu23a/hu23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-hu23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Diyi family: Hu - given: Chi family: Zhang - given: Viktor family: Prasanna - given: Bhaskar family: Krishnamachari editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 467-482 id: hu23a issued: date-parts: - 2023 - 4 - 13 firstpage: 467 lastpage: 482 published: 2023-04-13 00:00:00 +0000 - title: 'Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs' abstract: 'Most existing deep neural networks (DNNs) are easily disturbed by slight noise. However, there are few researches on physical attacks by deploying lighting equipment. The light-based physical attacks has excellent covertness, which brings great security risks to many vision-based applications (such as self-driving). Therefore, we propose a light-based physical attack, called adversarial laser spot (AdvLS), which optimizes the physical parameters of laser spots through genetic algorithm to perform physical attacks. It realizes robust and covert physical attack by using low-cost laser equipment. As far as we know, AdvLS is the first light-based physical attack that perform physical attacks in the daytime. A large number of experiments in the digital and physical environments show that AdvLS has excellent robustness and covertness. In addition, through in-depth analysis of the experimental data, we find that the adversarial perturbations generated by AdvLS have superior adversarial attack migration. The experimental results show that AdvLS impose serious interference to advanced DNNs, we call for the attention of the proposed AdvLS.' volume: 189 URL: https://proceedings.mlr.press/v189/hu23b.html PDF: https://proceedings.mlr.press/v189/hu23b/hu23b.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-hu23b.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Chengyin family: Hu - given: Yilong family: Wang - given: Kalibinuer family: Tiliwalidi - given: Wen family: Li editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 483-498 id: hu23b issued: date-parts: - 2023 - 4 - 13 firstpage: 483 lastpage: 498 published: 2023-04-13 00:00:00 +0000 - title: '3D Manifold Topology Based Medical Image Data Augmentation' abstract: 'Data augmentation is an effective and universal technique for improving the generalization performance of deep neural networks. Current data augmentation implementations usually involve geometric and photometric transformations. However, none of them considers the topological information in images, which is an important global invariant of the three-dimensional manifold. In our implementation, we design a novel method that finds the generator of the first homology group, i.e. closed loops cannot shrink to a point, of 3D image and erases the bounding box of a random loop. To the best of our knowledge, it is the first time that data augmentation based on the first homology group of the three-dimensional image is applied in medical image augmentation. Our numerical experiments demonstrate that the proposed approach outperforms the state-of-the-art method.' volume: 189 URL: https://proceedings.mlr.press/v189/huang23a.html PDF: https://proceedings.mlr.press/v189/huang23a/huang23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-huang23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Jisui family: Huang - given: Na family: Lei editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 499-514 id: huang23a issued: date-parts: - 2023 - 4 - 13 firstpage: 499 lastpage: 514 published: 2023-04-13 00:00:00 +0000 - title: 'Embedding Adaptation Network with Transformer for Few-Shot Action Recognition' abstract: 'Few-shot action recognition aims to classify novel action categories using a few training samples. Most current few-shot action recognition methods via episodic training strategy mainly use the same normalization method to normalize feature embeddings, leading to limited performance when the batch size is small. And some methods learn feature embeddings individually without considering the whole task, neglecting important interactive information between videos in the current episode. To address these problems, we propose a novel embedding adaptation network with Transformer (EANT) for few-shot action recognition. Specifically, we first propose an improved self-guided instance normalization (SGIN) module to adaptively learn class-specific feature embeddings in an input-dependent manner. Built upon the learned feature embeddings, we design a Transformer-based embedding learning (TEL) module to learn task-specific feature embeddings by fully capturing rich information cross videos in each episodic task. Furthermore, we utilize semantic knowledge among all sampled training classes as additional supervisory information to improve the generalization ability of the network. By this means, the proposed EANT can be highly effective and informative for few-shot action recognition. Extensive experiments conducted on several challenging few-shot action recognition benchmarks show that the proposed EANT outperforms several state-of-the-art methods by a large margin.' volume: 189 URL: https://proceedings.mlr.press/v189/jin23a.html PDF: https://proceedings.mlr.press/v189/jin23a/jin23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-jin23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Rongrong family: Jin - given: Xiao family: Wang - given: Guangge family: Wang - given: Yang family: Lu - given: Hai-Miao family: Hu - given: Hanzi family: Wang editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 515-530 id: jin23a issued: date-parts: - 2023 - 4 - 13 firstpage: 515 lastpage: 530 published: 2023-04-13 00:00:00 +0000 - title: 'Deep Reinforcement Learning for High-Frequency Market Making' abstract: 'High-frequency market making is a algorithmic trading strategy in which an agent provides liquidity at the same time as quoting a bid price and an ask price on a security. The strategy reap profits in the form of the spread between the quoted price placed on the buy and sell prices. Due to complexity in inventory risk, counterparties to trades and information asymmetry, the understanding of high-frequency market making algorithms is relatively unexplored by academics across disciplines. In this paper, we develop realistic simulations of limit order markets and use them to design a high-frequency market making agent using Deep Recurrent Q-Networks. Our approach outperforms a prominent benchmark strategy from literature, which uses temporal-difference reinforcement learning to design market making agents. Using the simulation framework, we analyse how the maker-take fee, a feature of market design, affects market quality and the agent’s profitability. The agents successfully reproduce stylised facts in historical trade data from each simulation.' volume: 189 URL: https://proceedings.mlr.press/v189/kumar23a.html PDF: https://proceedings.mlr.press/v189/kumar23a/kumar23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-kumar23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Pankaj family: Kumar editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 531-546 id: kumar23a issued: date-parts: - 2023 - 4 - 13 firstpage: 531 lastpage: 546 published: 2023-04-13 00:00:00 +0000 - title: 'Probabilistic Adaptive Spatial-Temporal Regularized Correlation Filters for UAV Tracking' abstract: 'Most existing trackers based on spatial-temporal regularized correlation filters exploit response map variation to adapt regularization terms to object appearance changes automatically. However, these trackers ignore the high uncertainty of the response map when the object is occluded or similar objects around, making them unable to learn reliable filters accurately. Furthermore, most correlation filters use linear interpolation directly to update the filter model at each frame, which may cause model degradation once the tracking result is inaccurate or missing. In this work, we propose a novel probabilistic adaptive spatial-temporal regularized correlation filters (PASTRCF) to solve the two issues mentioned above. A probabilistic model constructing the reliability of the response map is introduced to accurately utilize the information in the response map to learn regularization coefficients adaptively. The adaptive threshold mechanism provides an appropriate strategy to update the filter model to alleviate model degradation. Extensive experiments on UAV benchmarks have proven the favorable performance of our method compared to the state-of-art trackers, with robust tracking while ensuring real-time performance.' volume: 189 URL: https://proceedings.mlr.press/v189/li23b.html PDF: https://proceedings.mlr.press/v189/li23b/li23b.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-li23b.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Rui family: Li - given: Xiao family: Li editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 547-562 id: li23b issued: date-parts: - 2023 - 4 - 13 firstpage: 547 lastpage: 562 published: 2023-04-13 00:00:00 +0000 - title: 'Contrastive Inductive Bias Controlling Networks for Reinforcement Learning' abstract: 'Effective learning in an visual-based environment is essential for reinforcement learning (RL) agent, while it has been empirically observed that learning from high dimensional observations such as raw pixels is sample-inefficient. For common practice, RL algorithms for image input often use encoders composed of CNNs to extract useful features from high dimensional observations. Recent studies have shown that CNNs have strong inductive bias towards image styles rather than content (i.e. agent shapes), while content is the information that RL algorithms should focus on. Inspired by this, we suggest reducing the intrinsic style bias of CNNs by proposing Contrastive Inductive Bias Controlling Networks for RL. It can help RL algorithms effectively focus on truly noteworthy information like agents’ own characteristics. Our approach incorporates two transfer networks and feature encoder with contrastive learning methods, guiding RL algorithms to learn more efficiently with sampling. Extensive experiments show that the extended framework greatly enhances the performance of existing model-free methods (i.e. SAC), enabling it to reach state-of-the-art performance on the DeepMind control suite benchmark.' volume: 189 URL: https://proceedings.mlr.press/v189/li23a.html PDF: https://proceedings.mlr.press/v189/li23a/li23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-li23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Dongxu family: Li - given: Shaochen family: Wang - given: Kang family: Chen - given: Bin family: Li editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 563-578 id: li23a issued: date-parts: - 2023 - 4 - 13 firstpage: 563 lastpage: 578 published: 2023-04-13 00:00:00 +0000 - title: 'AIIR-MIX: Multi-Agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network' abstract: 'Deducing the contribution of each agent and assigning the corresponding reward to them is a crucial problem in cooperative Multi-Agent Reinforcement Learning (MARL). Previous studies try to resolve the issue through designing an intrinsic reward function, but the intrinsic reward is simply combined with the environment reward by summation in these studies, which makes the performance of their MARL framework unsatisfactory. We propose a novel method named Attention Individual Intrinsic Reward Mixing Network (AIIR-MIX) in MARL, and the contributions of AIIR-MIX are listed as follows: \textbf{(a)} we construct a novel intrinsic reward network based on the attention mechanism to make teamwork more effective. \textbf{(b)} we propose a Mixing network that is able to combine intrinsic and extrinsic rewards non-linearly and dynamically in response to changing conditions of the environment. We compare AIIR-MIX with many State-Of-The-Art (SOTA) MARL methods on battle games in StarCraft II. And the results demonstrate that AIIR-MIX performs admirably and can defeat the current advanced methods on average test win rate. To validate the effectiveness of AIIR-MIX, we conduct additional ablation studies. The results show that AIIR-MIX can dynamically assign each agent a real-time intrinsic reward in accordance with their actual contribution.' volume: 189 URL: https://proceedings.mlr.press/v189/li23d.html PDF: https://proceedings.mlr.press/v189/li23d/li23d.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-li23d.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Wei family: Li - given: Weiyan family: Liu - given: Shitong family: Shao - given: Shiyi family: Huang editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 579-594 id: li23d issued: date-parts: - 2023 - 4 - 13 firstpage: 579 lastpage: 594 published: 2023-04-13 00:00:00 +0000 - title: 'Unsupervised Photo-to-Caricature Generation with Adaptive Select Layer-Instance Normalization and Semi-cycle Consistency' abstract: 'Unpaired photo to caricature generation is a challenging but meaningful task. Generating high quality caricatures with rich texture/color and plausible exaggeration is important. Previous methods often respectively deal with the shape transformation and texture/color style. We argue that shape transformation can be treated as same as texture/color. Thereby, shape transformation and texture/color can be transferred at the same time. In this paper, we proposed a new method namely AdsSe-GAN for photo-to-caricature generation, which consists of a new normalization function called AdaSLIN and a new semi-cycle consistency loss. The AdaSLIN adaptively selects Layer Normalization or Instance Normalization to simultaneously transfer texture/color and shape transformation. Besides we present semi-cycle consistency loss which only imposes L1 norm on caricature-to-photo process, which is different from existing methods that apply cycle consistency loss to preserve the original domain information. In fact, while generating caricature, taking no account of the cycle restriction makes our model generate caricature with more distinct exaggeration and higher quality. Experimental results on a public caricature dataset, WebCaricature, show the effectiveness of our proposed method compared with the state-of-the-art models.' volume: 189 URL: https://proceedings.mlr.press/v189/zhiwei23a.html PDF: https://proceedings.mlr.press/v189/zhiwei23a/zhiwei23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-zhiwei23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Li family: Zhiwei - given: Cai family: Weiling - given: Cairun family: Wang editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 595-610 id: zhiwei23a issued: date-parts: - 2023 - 4 - 13 firstpage: 595 lastpage: 610 published: 2023-04-13 00:00:00 +0000 - title: 'Robust Direct Learning for Causal Data Fusion' abstract: 'In the era of big data, the explosive growth of multi-source heterogeneous data offers many exciting challenges and opportunities for improving the inference of conditional average treatment effects. In this paper, we investigate homogeneous and heterogeneous causal data fusion problems under a general setting that allows for the presence of source-specific covariates. We provide a direct learning framework for integrating multi-source data that separates the treatment effect from other nuisance functions, and achieves double robustness against certain misspecification. To improve estimation precision and stability, we propose a causal information-aware weighting function motivated by theoretical insights from the semiparametric efficiency theory; it assigns larger weights to samples containing more causal information with high interpretability. We introduce a two-step algorithm, the weighted multi-source direct learner, based on constructing a pseudo-outcome and regressing it on covariates under a weighted least square criterion; it offers us a powerful tool for causal data fusion, enjoying the advantages of easy implementation, double robustness and model flexibility. In simulation studies, we demonstrate the effectiveness of our proposed methods in both homogeneous and heterogeneous causal data fusion scenarios.' volume: 189 URL: https://proceedings.mlr.press/v189/li23c.html PDF: https://proceedings.mlr.press/v189/li23c/li23c.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-li23c.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Xinyu family: Li - given: Yilin family: Li - given: Qing family: Cui - given: Longfei family: Li - given: Jun family: Zhou editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 611-626 id: li23c issued: date-parts: - 2023 - 4 - 13 firstpage: 611 lastpage: 626 published: 2023-04-13 00:00:00 +0000 - title: 'Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes' abstract: 'Reinforcement learning (RL) algorithms can be used to provide personalized services, which rely on users’ private and sensitive data. To protect the users’ privacy, privacy-preserving RL algorithms are in demand. In this paper, we study RL with linear function approximation and local differential privacy (LDP) guarantees. We propose a novel $(\varepsilon, \delta)$-LDP algorithm for learning a class of Markov decision processes (MDPs) dubbed linear mixture MDPs, and obtains an $\tilde{\mathcal{O}}( d^{5/4}H^{7/4}T^{3/4}\left(\log(1/\delta)\right)^{1/4}\sqrt{1/\varepsilon})$ regret, where $d$ is the dimension of feature mapping, $H$ is the length of the planning horizon, and $T$ is the number of interactions with the environment. We also prove a lower bound $\Omega(dH\sqrt{T}/\left(e^{\varepsilon}(e^{\varepsilon}-1)\right))$ for learning linear mixture MDPs under $\varepsilon$-LDP constraint. Experiments on synthetic datasets verify the effectiveness of our algorithm. To the best of our knowledge, this is the first provable privacy-preserving RL algorithm with linear function approximation.' volume: 189 URL: https://proceedings.mlr.press/v189/liao23a.html PDF: https://proceedings.mlr.press/v189/liao23a/liao23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-liao23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Chonghua family: Liao - given: Jiafan family: He - given: Quanquan family: Gu editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 627-642 id: liao23a issued: date-parts: - 2023 - 4 - 13 firstpage: 627 lastpage: 642 published: 2023-04-13 00:00:00 +0000 - title: 'FF-Net: An End-to-end Feature-Fusion Network for Double JPEG Detection and Localization' abstract: 'In the real-world, most images are saved in JPEG format, so many forged images are partially or totally composed of JPEG images and then saved in JPEG format again. In this case, exposing forged images can be accomplished by the detection of double JPEG compressions. Although the detection methods of double JPEG compressions have greatly improved, they rely on handcrafted features of image patches and cannot locate forgery at pixel-level. To break this limitation, we propose an end-to-end feature-fusion network (FF-Net) for double compression detection and forgery localization. We find that JPEG compression fingerprint primarily exists on the high-frequency component of an image, and the singly and doubly compression yield different fingerprints. Therefore, we design two encoders cooperatively to learn the compression fingerprint directly from the whole image. A decoder is deployed to locate the regions with different compression fingerprints at pixel-level based on the learned compression fingerprint. The experiment results verify that the proposed FF-Net can detect and locate the forged regions more accurately than these existing detection methods. Besides, it has a good generalization ability that the network trained on one compression case can work in numerous compression cases. Moreover, it can detect different local forgeries, including copy-move, splicing, and object-removal.' volume: 189 URL: https://proceedings.mlr.press/v189/liu23a.html PDF: https://proceedings.mlr.press/v189/liu23a/liu23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-liu23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Bo family: Liu - given: Ranglei family: Wu - given: Xiuli family: Bi - given: Bin family: Xiao editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 643-657 id: liu23a issued: date-parts: - 2023 - 4 - 13 firstpage: 643 lastpage: 657 published: 2023-04-13 00:00:00 +0000 - title: 'AS-IntroVAE: Adversarial Similarity Distance Makes Robust IntroVAE' abstract: 'Recently, introspective models like IntroVAE and S-IntroVAE have excelled in image generation and reconstruction tasks. The principal characteristic of introspective models is the adversarial learning of VAE, where the encoder attempts to distinguish between the real and the fake (i.e., synthesized) images. However, due to the unavailability of an effective metric to evaluate the difference between the real and the fake images, the posterior collapse and the vanishing gradient problem still exist, reducing the fidelity of the synthesized images. In this paper, we propose a new variation of IntroVAE called Adversarial Similarity Distance Introspective Variational Autoencoder (AS-IntroVAE). We theoretically analyze the vanishing gradient problem and construct a new Adversarial Similarity Distance (AS-Distance) using the 2-Wasserstein distance and the kernel trick. With weight annealing on AS-Distance and KL-Divergence, the AS-IntroVAE are able to generate stable and high-quality images. The posterior collapse problem is addressed by making per-batch attempts to transform the image so that it better fits the prior distribution in the latent space. Compared with the per-image approach, this strategy fosters more diverse distributions in the latent space, allowing our model to produce images of great diversity. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of AS-IntroVAE on image generation and reconstruction tasks.' volume: 189 URL: https://proceedings.mlr.press/v189/changjie23a.html PDF: https://proceedings.mlr.press/v189/changjie23a/changjie23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-changjie23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Lu family: Changjie - given: Zheng family: Shen - given: Wang family: Zirui - given: Dib family: Omar - given: Gupta family: Gaurav editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 658-673 id: changjie23a issued: date-parts: - 2023 - 4 - 13 firstpage: 658 lastpage: 673 published: 2023-04-13 00:00:00 +0000 - title: 'Multi-Scale Anomaly Detection for Time Series with Attention-based Recurrent Autoencoders' abstract: 'Anomaly detection on time series is an important research topic in data mining, which has a wide range of applications in financial markets, biological data, information technology, manufacturing system, etc. However, the existing time series anomaly detection methods mainly capture temporal features from a single-scale viewpoint, which cannot detect multi-scale anomalies effectively. In this paper, we propose a novel approach of Multi-scale Anomaly Detection for Time Series (MAD-TS) with an attention-based recurrent autoencoder model to solve the above problem. The proposed method adopts a hierarchically connected recurrent encoder to extract the features of a time series from different levels. The multi-scale features are then fused by a hierarchical decoder with attention mechanism to reconstruct the original sequence at different scales. Based on the reconstruction errors at multiple scales, anomaly scores can be learned for different data points, which can be used to infer the anomaly status of the time series. Extensive experiments based on five open time series datasets show that the proposed MAD-TS method achieves significant performance improvement on anomaly detection compared to the state-of-the-arts.' volume: 189 URL: https://proceedings.mlr.press/v189/qingning23a.html PDF: https://proceedings.mlr.press/v189/qingning23a/qingning23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-qingning23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Lu family: Qingning - given: Li family: Wenzhong - given: Zhu family: Chuanze - given: Chen family: Yizhou - given: Wang family: Yinke - given: Zhang family: Zhijie - given: Shen family: Linshan - given: Lu family: Sanglu editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 674-689 id: qingning23a issued: date-parts: - 2023 - 4 - 13 firstpage: 674 lastpage: 689 published: 2023-04-13 00:00:00 +0000 - title: 'Learning Disentangled Representation in Pruning for Real-Time UAV Tracking' abstract: 'Efficiency is a critical issue in UAV tracking because of the limitations of computing resources, battery capacity, and maximum load of unmanned aerial vehicle (UAV). However, deep learning (DL)-based trackers hardly achieve real-time tracking on a single CPU despite their high tracking precision. To the contrary, discriminative correlation filters (DCF)-based trackers have high efficiency but their precision is barely satisfactory. Despite the precision is inferior, DCF-based trackers instead of DL-based ones are widely applied in UAV tracking to trade precision for efficiency. This paper aims to improve the efficiency of the DL-based tracker SiamFC++, in particular, for UAV tracking using the model compression technique, i.e., rank-based filter pruning, which has not been well explored before. Meanwhile, to combat the potential loss of precision caused by pruning we exploit disentangled representation learning to disentangle the output feature of the backbone into two parts: the identity-related features and the identity-unrelated features. Only the identity-related features are used for subsequent classification and regression tasks to improve the effectiveness of the feature representation. With the proposed disentangled representation in pruning, we achieved higher precisions when compressing the original model SiamFC++ with a global pruning ratio of 0.5. Extensive experiments on four public UAV benchmarks, i.e., UAV123@10fps, UAVDT, DTB70, and Vistrone2018, show that the proposed tracker DP-SiamFC++ strikes a remarkable balance between efficiency and precision, and achieves state-of-the-art performance in UAV tracking.' volume: 189 URL: https://proceedings.mlr.press/v189/ma23a.html PDF: https://proceedings.mlr.press/v189/ma23a/ma23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-ma23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Siyu family: Ma - given: Yuting family: Liu - given: Dan family: Zeng - given: Yaxin family: Liao - given: Xiaoyu family: Xu - given: Shuiwang family: Li editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 690-705 id: ma23a issued: date-parts: - 2023 - 4 - 13 firstpage: 690 lastpage: 705 published: 2023-04-13 00:00:00 +0000 - title: 'RoLNiP: Robust Learning Using Noisy Pairwise Comparisons' abstract: 'This paper presents a robust approach for learning from noisy pairwise comparisons. We propose sufficient conditions on the loss function under which the risk minimization frame- work becomes robust to noise in the pairwise similar dissimilar data. Our approach does not require the knowledge of noise rate in the uniform noise case. In the case of conditional noise, the proposed method depends on the noise rates. For such cases, we offer a provably correct approach for estimating the noise rates. Thus, we propose an end-to-end approach to learning robust classifiers in this setting. We experimentally show that the proposed approach RoLNiP outperforms the robust state-of-the-art methods for learning with noisy pairwise comparisons.' volume: 189 URL: https://proceedings.mlr.press/v189/maheshwara23a.html PDF: https://proceedings.mlr.press/v189/maheshwara23a/maheshwara23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-maheshwara23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Samartha S. family: Maheshwara - given: Naresh family: Manwani editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 706-721 id: maheshwara23a issued: date-parts: - 2023 - 4 - 13 firstpage: 706 lastpage: 721 published: 2023-04-13 00:00:00 +0000 - title: 'Asynchronous Personalized Federated Learning with Irregular Clients' abstract: 'To provide intelligent and personalized models for clients, personalized federated learning (PFL) enables learning from data, identifying patterns, and making automated decisions in a privacy-preserving manner. PFL involves independent training for multiple clients with synchronous aggregation steps. However, the assumptions made by existing works are not realistic given the heterogeneity of clients. In particular, the volume and distribution of collected data vary in the training process, and the clients also vary in their available system configurations, which leads to vast heterogeneity in the system. To address these challenges, we present an \textit{asynchronous} method (AsyPFL), where clients learn personalized models w.r.t. local data by making the most informative parameters less volatile. The central server aggregates model parameters asynchronously. In addition, we also reformulate PFL by unifying both synchronous and asynchronous updating schemes with an asynchrony-related parameter. Theoretically, we show that AsyPFL’s convergence rate is state-of-the-art and provide guarantees of choosing key hyperparameters optimally. With these theoretical guarantees, we validate AsyPFL on different tasks with non-IID and staleness settings. The results indicate that, given a large proportion of irregular clients, AsyPFL excels at empirical performance compared with vanilla PFL algorithms on non-IID and IID cases.' volume: 189 URL: https://proceedings.mlr.press/v189/ma23b.html PDF: https://proceedings.mlr.press/v189/ma23b/ma23b.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-ma23b.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Zichen family: Ma - given: Yu family: Lu - given: Wenye family: Li - given: Shuguang family: Cui editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 706-721 id: ma23b issued: date-parts: - 2023 - 4 - 13 firstpage: 706 lastpage: 721 published: 2023-04-13 00:00:00 +0000 - title: 'Efficient Deep Clustering of Human Activities and How to Improve Evaluation' abstract: 'There has been much recent research on human activity recognition (HAR), due to the proliferation of wearable sensors in watches and phones, and the advances of deep learning methods, which avoid the need to manually extract features from raw sensor signals. A significant disadvantage of deep learning applied to HAR is the need for manually labelled training data, which is especially difficult to obtain for HAR datasets. Progress is starting to be made in the unsupervised setting, in the form of deep HAR clustering models, which can assign labels to data without having been given any labels to train on, but there are problems with evaluating deep HAR clustering models, which makes assessing the field and devising new methods difficult. In this paper, we highlight several distinct problems with how deep HAR clustering models are evaluated, describing these problems in detail and conducting careful experiments to explicate the effect that they can have on results. Additionally, we present a new deep clustering model for HAR. When tested under our proposed settings, our model performs better than (or on par with) existing models, while also being more efficient and scalable by avoiding the need for an autoencoder.' volume: 189 URL: https://proceedings.mlr.press/v189/mahon23a.html PDF: https://proceedings.mlr.press/v189/mahon23a/mahon23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-mahon23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Louis family: Mahon - given: Thomas family: Lukasiewicz editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 722-737 id: mahon23a issued: date-parts: - 2023 - 4 - 13 firstpage: 722 lastpage: 737 published: 2023-04-13 00:00:00 +0000 - title: 'Bootstrapping a high quality multilingual multimodal dataset for Bletchley' abstract: 'Vision-language models have recently made impressive strides, primarily driven by large-scale training on web data. While pioneering works such as CLIP and ALIGN show significant improvements, these are focused on English data as it is easy to source them from the web. Towards serving non-English-speaking demographics, we consider various methods for generating multilingual data and find that a simple bootstrapping mechanism works surprisingly well. Specifically, just using English image captions data and text-only multilingual translation pairs we train a fairly strong multilingual vision-language model and then leverage it to create a much cleaner version of the multilingual image captions dataset we collected. We demonstrate that this dataset which was used to train Bletchley result in a strong multi-modal and multilingual model which reaches strong performance across several multilingual zero-shot tasks. Specifically, Bletchley achieves state-of-the-art results on multilingual COCO, Multi30k sets, IGLUE WIT and xFlickr&CO datasets.' volume: 189 URL: https://proceedings.mlr.press/v189/mohammed23a.html PDF: https://proceedings.mlr.press/v189/mohammed23a/mohammed23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-mohammed23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Owais Khan family: Mohammed - given: Kriti family: Aggarwal - given: Qiang family: Liu - given: Saksham family: Singhal - given: Johan family: Bjorck - given: Subhojit family: Som editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 738-753 id: mohammed23a issued: date-parts: - 2023 - 4 - 13 firstpage: 738 lastpage: 753 published: 2023-04-13 00:00:00 +0000 - title: 'Hashing2Vec: Fast Embedding Generation for SARS-CoV-2 Spike Sequence Classification' abstract: ' Due to the ongoing coronavirus (COVID-19) pandemic, an unprecedented amount of SARS-CoV-2 sequence data is available. The scale of this data has out-paced traditional methods for its analysis, while machine-learning approaches aimed at clustering and classification of SARS-CoV-2 variants is becoming an attractive alternative. Since the SARS-CoV-2 genome is highly dimensional, considering the much smaller spike region can save a great deal of processing. As the spike protein mediates the attachment of the coronavirus to the host cell, most of the newer and more contagious variants can be characterized by alterations to the spike protein; hence it is often sufficient for characterizing the different SARS-CoV-2 variants. Another important consideration is to have a fast feature embedding generation, which is the subject of this work. Applying any machine learning (ML) model to a biological sequence requires first transforming it into a fixed-length (numerical) form. While there exist several compact embeddings for SARS-CoV-2 spike protein sequences, the generation process is computationally expensive since the features, added to the resulting vectors, are indexed in a naïve fashion. To solve this problem, we propose a fast and alignment-free hashing-based approach to design a fixed-length feature embedding for spike protein sequences, called Hashing2Vec, which can be used as input to any standard ML model. Using real-world data, we show that the proposed embedding is not only efficient to compute but also outperforms current state-of-the-art embedding methods in terms of classification accuracy. In terms of runtime, we achieve up to a 99.8% improvement in the Hashing2Vec-based embedding generation as compared to the baselines on a set of 7K spike amino acid sequences. It also outperforms the baselines on this data in terms of predictive performance and achieves accuracy and ROC-AUC scores of 86% and 84.4%, respectively.' volume: 189 URL: https://proceedings.mlr.press/v189/taslim23a.html PDF: https://proceedings.mlr.press/v189/taslim23a/taslim23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-taslim23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Murad family: Taslim - given: Chourasia family: Prakash - given: Ali family: Sarwan - given: Patterson family: Murray editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 754-769 id: taslim23a issued: date-parts: - 2023 - 4 - 13 firstpage: 754 lastpage: 769 published: 2023-04-13 00:00:00 +0000 - title: 'Robust computation of optimal transport by $β$-potential regularization' abstract: 'Optimal transport (OT) has become a widely used tool in the machine learning field to measure the discrepancy between probability distributions. For instance, OT is a popular loss function that quantifies the discrepancy between an empirical distribution and a parametric model. Recently, an entropic penalty term and the celebrated Sinkhorn algorithm have been commonly used to approximate the original OT in a computationally efficient way. However, since the Sinkhorn algorithm runs a projection associated with the Kullback-Leibler divergence, it is often vulnerable to outliers. To overcome this problem, we propose regularizing OT with the $\beta$-potential term associated with the so-called $\beta$-divergence, which was developed in robust statistics. Our theoretical analysis reveals that the $\beta$-potential can prevent the mass from being transported to outliers. We experimentally demonstrate that the transport matrix computed with our algorithm helps estimate a probability distribution robustly even in the presence of outliers. In addition, our proposed method can successfully detect outliers from a contaminated dataset.' volume: 189 URL: https://proceedings.mlr.press/v189/nakamura23a.html PDF: https://proceedings.mlr.press/v189/nakamura23a/nakamura23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-nakamura23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Shintaro family: Nakamura - given: Han family: Bao - given: Masashi family: Sugiyama editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 770-785 id: nakamura23a issued: date-parts: - 2023 - 4 - 13 firstpage: 770 lastpage: 785 published: 2023-04-13 00:00:00 +0000 - title: 'BINAS: Bilinear Interpretable Neural Architecture Search' abstract: 'Realistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others. A popular approach to find fitting networks is through constrained Neural Architecture Search (NAS). However, previous methods use complicated predictors for the accuracy of the network. Those predictors are hard to interpret and sensitive to many hyperparameters to be tuned, hence, the resulting accuracy of the generated models is often harmed. In this work we resolve this by introducing Bilinear Interpretable Neural Architecture Search (BINAS), that is based on an accurate and simple bilinear formulation of both an accuracy estimator and the expected resource requirement, together with a scalable search method with theoretical guarantees. The simplicity of our proposed estimator together with the intuitive way it is constructed bring interpretability through many insights about the contribution of different design choices. For example, we find that in the examined search space, adding depth and width is more effective at deeper stages of the network and at the beginning of each resolution stage. Our experiments show that BINAS generates comparable to or better architectures than other state-of-the-art NAS methods within a reduced search cost for each additional generated network, while strictly satisfying the resource constraints.' volume: 189 URL: https://proceedings.mlr.press/v189/nayman23a.html PDF: https://proceedings.mlr.press/v189/nayman23a/nayman23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-nayman23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Niv family: Nayman - given: Yonathan family: Aflalo - given: Asaf family: Noy - given: Lihi family: Zelnik-Manor editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 786-801 id: nayman23a issued: date-parts: - 2023 - 4 - 13 firstpage: 786 lastpage: 801 published: 2023-04-13 00:00:00 +0000 - title: 'One Gradient Frank-Wolfe for Decentralized Online Convex and Submodular Optimization' abstract: 'Decentralized learning has been studied intensively in recent years motivated by its wide applications in the context of federated learning. The majority of previous research focuses on the offline setting in which the objective function is static. However, the offline setting becomes unrealistic in numerous machine learning applications that witness the change of massive data. In this paper, we propose \emph{decentralized online} algorithm for convex and continuous DR-submodular optimization, two classes of functions that are present in a variety of machine learning problems. Our algorithms achieve performance guarantees comparable to those in the centralized offline setting. Moreover, on average, each participant performs only a \emph{single} gradient computation per time step. Subsequently, we extend our algorithms to the bandit setting. Finally, we illustrate the competitive performance of our algorithms in real-world experiments.' volume: 189 URL: https://proceedings.mlr.press/v189/nguyen23a.html PDF: https://proceedings.mlr.press/v189/nguyen23a/nguyen23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-nguyen23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Tuan-Anh family: Nguyen - given: Nguyen family: Kim Thang - given: Denis family: Trystram editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 802-815 id: nguyen23a issued: date-parts: - 2023 - 4 - 13 firstpage: 802 lastpage: 815 published: 2023-04-13 00:00:00 +0000 - title: 'Example or Prototype? Learning Concept-Based Explanations in Time-Series' abstract: 'With the continuous increase of deep learning applications in safety critical systems, the need for an interpretable decision-making process has become a priority within the research community. While there are many existing explainable artificial intelligence algorithms, a systematic assessment of the suitability of global explanation methods for different applications is not available. In this paper, we respond to this demand by systematically comparing two existing global concept-based explanation methods with our proposed global, model-agnostic concept-based explanation method for time-series data. This method is based on an autoencoder structure and derives abstract global explanations called "prototypes". The results of a human user study and a quantitative analysis show a superior performance of the proposed method, but also highlight the necessity of tailoring explanation methods to the target audience of machine learning models.' volume: 189 URL: https://proceedings.mlr.press/v189/obermair23a.html PDF: https://proceedings.mlr.press/v189/obermair23a/obermair23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-obermair23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Christoph family: Obermair - given: Alexander family: Fuchs - given: Franz family: Pernkopf - given: Lukas family: Felsberger - given: Andrea family: Apollonio - given: Daniel family: Wollmann editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 816-831 id: obermair23a issued: date-parts: - 2023 - 4 - 13 firstpage: 816 lastpage: 831 published: 2023-04-13 00:00:00 +0000 - title: 'On the Interpretability of Attention Networks' abstract: 'Attention mechanisms form a core component of several successful deep learning architectures, and are based on one key idea: “The output depends only on a small (but unknown) segment of the input.” In several practical applications like image captioning and language translation, this is mostly true. In trained models with an attention mechanism, the outputs of an intermediate module that encodes the segment of input responsible for the output is often used as a way to peek into the ‘reasoning’ of the network. We make such a notion more precise for a variant of the classification problem that we term selective dependence classification (SDC) when used with attention model architectures. Under such a setting, we demonstrate various error modes where an attention model can be accurate but fail to be interpretable, and show that such models do occur as a result of training. We illustrate various situations that can accentuate and mitigate this behaviour. Finally, we use our objective definition of interpretability for SDC tasks to evaluate a few attention model learning algorithms designed to encourage sparsity and demonstrate that these algorithms help improve interpretability.' volume: 189 URL: https://proceedings.mlr.press/v189/pandey23a.html PDF: https://proceedings.mlr.press/v189/pandey23a/pandey23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-pandey23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Lakshmi Narayan family: Pandey - given: Rahul family: Vashisht - given: Harish G. family: Ramaswamy editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 832-847 id: pandey23a issued: date-parts: - 2023 - 4 - 13 firstpage: 832 lastpage: 847 published: 2023-04-13 00:00:00 +0000 - title: 'Dynamic Forward and Backward Sparse Training (DFBST): Accelerated Deep Learning through Completely Sparse Training Schedule' abstract: 'Neural network sparsification has received a lot of attention in recent years. A number of dynamic sparse training methods have been developed that achieve significant sparsity levels during training, ensuring comparable performance to their dense counterparts. However, most of these methods update all the model parameters using dense gradients. To this end, gradient sparsification is achieved either by non-dynamic (fixed) schedule or computationally expensive dynamic pruning schedule. To alleviate these drawbacks, we propose Dynamic Forward and Backward Sparse Training (DFBST), an algorithm which dynamically sparsifies both the forward and backward passes using trainable masks, leading to a completely sparse training schedule. In contrast to existing sparse training methods, we propose separate learning for forward as well as backward masks. Our approach achieves state of the art performance in terms of both accuracy and sparsity compared to existing dynamic pruning algorithms on benchmark datasets, namely MNIST, CIFAR-10 and CIFAR-100.' volume: 189 URL: https://proceedings.mlr.press/v189/pote23a.html PDF: https://proceedings.mlr.press/v189/pote23a/pote23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-pote23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Tejas family: Pote - given: Muhammad Athar family: Ganaie - given: Atif family: Hassan - given: Swanand family: Khare editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 848-863 id: pote23a issued: date-parts: - 2023 - 4 - 13 firstpage: 848 lastpage: 863 published: 2023-04-13 00:00:00 +0000 - title: 'Interpretable Representation Learning from Temporal Multi-view Data' abstract: 'In many scientific problems such as video surveillance, modern genomics, and finance, data are often collected from diverse measurements across time that exhibit time-dependent heterogeneous properties. Thus, it is important to not only integrate data from multiple sources (called multi-view data), but also to incorporate time dependency for deep understanding of the underlying system. We propose a generative model based on variational autoencoder and a recurrent neural network to infer the latent dynamics for multi-view temporal data. This approach allows us to identify the disentangled latent embeddings across views while accounting for the time factor. We invoke our proposed model for analyzing three datasets on which we demonstrate the effectiveness and the interpretability of the model.' volume: 189 URL: https://proceedings.mlr.press/v189/qiu23a.html PDF: https://proceedings.mlr.press/v189/qiu23a/qiu23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-qiu23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Lin family: Qiu - given: Vernon M. family: Chinchilli - given: Lin family: Lin editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 864-879 id: qiu23a issued: date-parts: - 2023 - 4 - 13 firstpage: 864 lastpage: 879 published: 2023-04-13 00:00:00 +0000 - title: 'AFRNN: Stable RNN with Top Down Feedback and Antisymmetry' abstract: 'Recurrent Neural Networks are an integral part of modern machine learning. They are good at performing tasks on sequential data. However, long sequences are still a problem for those models due to the well-known exploding/vanishing gradient problem. In this work, we build on recent approaches to interpreting the gradient problem as instability of the underlying dynamical system. We extend previous approaches to systems with top-down feedback, which is abundant in biological neural networks. We prove that the resulting system is stable for arbitrary depth and width and confirm this empirically. We further show that its performance is on par with LSTM and related approaches on standard benchmarks.' volume: 189 URL: https://proceedings.mlr.press/v189/schwabe23a.html PDF: https://proceedings.mlr.press/v189/schwabe23a/schwabe23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-schwabe23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Tim family: Schwabe - given: Tobias family: Glasmachers - given: Maribel family: Acosta editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 880-894 id: schwabe23a issued: date-parts: - 2023 - 4 - 13 firstpage: 880 lastpage: 894 published: 2023-04-13 00:00:00 +0000 - title: 'Autonomous Myocardial Infarction Detection from Electrocardiogram with a Multi Label Classification Approach' abstract: 'Myocardial Infarctions (MI) or heart attacks are among the most common medical emergencies globally. Such an episode often has mild or varied symptoms, making it hard to diagnose and respond in a timely manner. An electrocardiogram (ECG) is used to analyze the heart’s electrical activity and, through this help, clinicians detect and localize a heart attack. However, interpretation of the ECG is made manually by trained professionals. In order to make this diagnosis more efficient, multiple methods have tried to automate the MI detection and localization process. In this work, we aim to create a more effective method of MI detection by restructuring the localization as a multi-label classification (MLC) problem, in which one set of attributes can belong to one or more classes. For this classification, features like the ST-deviation, T wave amplitude, and R-S ratios have been extracted and fed into the MLC model, which in our case, is a chain classifier of random forest. This proposed model will have five classes as the target, which represent the locations where an MI can occur. Our method achieves the best overall hamming accuracy of 81.49% in a k-fold cross validation test, with the highest accuracy for an individual class being 97.72% for anterior.' volume: 189 URL: https://proceedings.mlr.press/v189/singh23a.html PDF: https://proceedings.mlr.press/v189/singh23a/singh23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-singh23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Vishwa Mohan family: Singh - given: Vibhor family: Saran - given: Pooja family: Kadambi editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 911-926 id: singh23a issued: date-parts: - 2023 - 4 - 13 firstpage: 911 lastpage: 926 published: 2023-04-13 00:00:00 +0000 - title: 'On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data' abstract: 'In this paper, we study the problem of PAC learning halfspaces in the non-interactive local differential privacy model (NLDP). To breach the barrier of exponential sample complexity, previous results studied a relaxed setting where the server has access to some additional public but unlabeled data. We continue in this direction. Specifically, we consider the problem under the standard setting instead of the large margin setting studied before. Under different mild assumptions on the underlying data distribution, we propose two approaches that are based on the Massart noise model and self-supervised learning and show that it is possible to achieve sample complexities that are only linear in the dimension and polynomial in other terms for both private and public data, which significantly improve the previous results. Our methods could also be used for other private PAC learning problems.' volume: 189 URL: https://proceedings.mlr.press/v189/su23a.html PDF: https://proceedings.mlr.press/v189/su23a/su23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-su23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Jinyan family: Su - given: Jinhui family: Xu - given: Di family: Wang editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 927-941 id: su23a issued: date-parts: - 2023 - 4 - 13 firstpage: 927 lastpage: 941 published: 2023-04-13 00:00:00 +0000 - title: 'Feature Distribution Matching for Federated Domain Generalization' abstract: 'Multi-source domain adaptation has been intensively studied. The distribution shift in features inherent to specific domains causes the negative transfer problem, degrading a model’s generality to unseen tasks. In Federated Learning (FL), learned model parameters are shared to train a global model that leverages the underlying knowledge across client models trained on separate data domains. Nonetheless, the data confidentiality of FL hinders the effectiveness of traditional domain adaptation methods that require prior knowledge of different domain data. We propose a new federated domain generalization method called Federated Knowledge Alignment (FedKA). FedKA leverages feature distribution matching in a global workspace such that the global model can learn domain-invariant client features under the constraint of unknown client data. FedKA employs a federated voting mechanism that generates target domain pseudo-labels based on the consensus from clients to facilitate global model fine-tuning. We performed extensive experiments, including an ablation study, to evaluate the effectiveness of the proposed method in both image and text classification tasks using different model architectures. The empirical results show that FedKA achieves performance gains of 8.8% and 3.5% in Digit-Five and Office-Caltech10, respectively, and a gain of 0.7% in Amazon Review with extremely limited training data. Moreover, we studied the effectiveness of FedKA in alleviating the negative transfer of FL based on a new criterion called Group Effect. The results show that FedKA can reduce negative transfer, improving the performance gain via model aggregation by 4 times.' volume: 189 URL: https://proceedings.mlr.press/v189/sun23a.html PDF: https://proceedings.mlr.press/v189/sun23a/sun23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-sun23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Yuwei family: Sun - given: Ng family: Chong - given: Hideya family: Ochiai editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 942-957 id: sun23a issued: date-parts: - 2023 - 4 - 13 firstpage: 942 lastpage: 957 published: 2023-04-13 00:00:00 +0000 - title: 'Auto-Physics-Encoder: Using Physics-Informed Latent Layer Two-Way Physics Flow for Monitoring Systems with Unobservability' abstract: 'With the Internet of Everything (IoE) nowadays, monitoring edge systems is essential for coordinating everything into an IoE web. However, it is hard to monitor edge systems due to limited system information and limited sensors. To infer system information and provide robust monitoring capability, machine learning models were used to approximate mapping rules between different measurements. However, mapping rule learning using traditional machine learning tools is one way only, e.g., from measurement variables to the state vector variables. And, it is hard to be reverted, leading to over-fitting because of inconsistency between the forward and inverse learnings. Hence, we propose a structural deep neural network framework to provide a coherent two-way functional approximation. For physical regularization, we embed network size into the number of variables in the latent layers. We also utilize state sensors in the ‘latent layer’ to guide other latent variables to create state sets. The performance of reconstruction for the two-way mapping rule is validated extensively using test cases in the engineering, physics, and mathematical analysis domain.' volume: 189 URL: https://proceedings.mlr.press/v189/sundaray23a.html PDF: https://proceedings.mlr.press/v189/sundaray23a/sundaray23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-sundaray23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Priyabrata family: Sundaray - given: Yang family: Weng editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 958-973 id: sundaray23a issued: date-parts: - 2023 - 4 - 13 firstpage: 958 lastpage: 973 published: 2023-04-13 00:00:00 +0000 - title: 'CVaR-Regret Bounds for Multi-armed Bandits' abstract: 'In contrast to risk-averse multi-armed bandit (MAB), where one aims for a best risk-sensitive arm while having a risk-neutral attitude when running the risk-averse MAB algorithm, in this paper, we aim for a best arm with respect to the mean like in the standard MAB, but we adopt a risk-averse attitude when running a standard MAB algorithm. Conditional value-at-risk (CVaR) of the regret is adopted as the metric to evaluate the performance of algorithms, which is an extension of the traditional expected regret minimization framework. For this new problem, we revisit several classic algorithms for stochastic and non-stochastic bandits, UCB, MOSS, and Exp3-IX with its variants and propose parameters with good theoretically guaranteed CVaR-regret, which match the results of the expected regret and achieve (nearly-)optimality up to constant. In the non-stochastic setting, we show that implicit exploration achieves a trade-off between the variability of the regret and the regret in expectation. Numerical experiments are conducted to validate our results.' volume: 189 URL: https://proceedings.mlr.press/v189/tan23a.html PDF: https://proceedings.mlr.press/v189/tan23a/tan23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-tan23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Chenmien family: Tan - given: Paul family: Weng editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 974-989 id: tan23a issued: date-parts: - 2023 - 4 - 13 firstpage: 974 lastpage: 989 published: 2023-04-13 00:00:00 +0000 - title: 'Multi-class Classification from Multiple Unlabeled Datasets with Partial Risk Regularization' abstract: 'Recent years have witnessed a great success of supervised deep learning, where predictive models were trained from a large amount of fully labeled data. However, in practice, labeling such big data can be very costly and may not even be possible for privacy reasons. Therefore, in this paper, we aim to learn an accurate classifier without any class labels. More specifically, we consider the case where multiple sets of unlabeled data and only their class priors, i.e., the proportions of each class, are available. Under this problem setup, we first derive an unbiased estimator of the classification risk that can be estimated from the given unlabeled sets and theoretically analyze the generalization error of the learned classifier. We then find that the classifier obtained as such tends to cause overfitting as its empirical risks go negative during training. To prevent overfitting, we further propose a partial risk regularization that maintains the partial risks with respect to unlabeled datasets and classes to certain levels. Experiments demonstrate that our method effectively mitigates overfitting and outperforms state-of-the-art methods for learning from multiple unlabeled sets.' volume: 189 URL: https://proceedings.mlr.press/v189/tang23a.html PDF: https://proceedings.mlr.press/v189/tang23a/tang23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-tang23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Yuting family: Tang - given: Nan family: Lu - given: Tianyi family: Zhang - given: Masashi family: Sugiyama editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 990-1005 id: tang23a issued: date-parts: - 2023 - 4 - 13 firstpage: 990 lastpage: 1005 published: 2023-04-13 00:00:00 +0000 - title: 'Domain Alignment Meets Fully Test-Time Adaptation' abstract: 'A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is to adapt a pre-trained model to novel domains using only unlabeled data. In this paper, we focus on a challenging variant of this problem, where access to the original source data is restricted. While fully test-time adaptation (FTTA) and unsupervised domain adaptation (UDA) are closely related, the advances in UDA are not readily applicable to TTA, since most UDA methods require access to the source data. Hence, we propose a new approach, CATTAn, that bridges UDA and FTTA, by relaxing the need to access entire source data, through a novel deep subspace alignment strategy. With a minimal overhead of storing the subspace basis set for the source data, CATTAn enables unsupervised alignment between source and target data during adaptation. Through extensive experimental evaluation on multiple 2D and 3D vision benchmar ks (ImageNet-C, Office-31, OfficeHome, DomainNet, PointDA-10) and model architectures, we demonstrate significant gains in FTTA performance. Furthermore, we make a number of crucial findings on the utility of the alignment objective even with inherently robust models, pre-trained ViT representations and under low sample availability in the target domain.' volume: 189 URL: https://proceedings.mlr.press/v189/thopalli23a.html PDF: https://proceedings.mlr.press/v189/thopalli23a/thopalli23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-thopalli23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Kowshik family: Thopalli - given: Pavan family: Turaga - given: Jayaraman J family: Thiagarajan editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1006-1021 id: thopalli23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1006 lastpage: 1021 published: 2023-04-13 00:00:00 +0000 - title: 'FLVoogd: Robust And Privacy Preserving Federated Learning' abstract: 'In this work, we propose FLVoogd, an updated federated learning method in which servers and clients collaboratively eliminate Byzantine attacks while preserving privacy. In particular, servers use automatic Density-based Spatial Clustering of Applications with Noise (DBSCAN) combined with Secure Multi-party Computation (SMPC) to cluster the benign majority without acquiring sensitive personal information. Meanwhile, clients build dual models and perform test-based distance controlling to adjust their local models toward the global one to achieve personalizing. Our framework is automatic and adaptive that servers/clients don’t need to tune the parameters during the training. In addition, our framework leverages SMPC’s operations, including multiplications, additions, and comparisons, where costly operations, like division and square root, are not required. Evaluations are carried out on some conventional datasets from the image classification field. The result shows that FLVoogd can effectively reject malicious uploads in most scenarios; meanwhile, it avoids data leakage from the server side.' volume: 189 URL: https://proceedings.mlr.press/v189/yuhang23a.html PDF: https://proceedings.mlr.press/v189/yuhang23a/yuhang23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-yuhang23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Tian family: Yuhang - given: Wang family: Rui - given: Qiao family: Yanqi - given: Panaousis family: Emmanouil - given: Liang family: Kaitai editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1022-1037 id: yuhang23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1022 lastpage: 1037 published: 2023-04-13 00:00:00 +0000 - title: 'Noise Robust Core-stable Coalitions of Hedonic Games' abstract: 'In this work, we consider the coalition formation games with an additional component, ‘noisy preferences’. Moreover, such noisy preferences are available only for a sample of coalitions. We propose a multiplicative noise model (equivalent to an additive noise model) and obtain the prediction probability, defined as the probability that the estimated PAC core-stable partition of the \emph{noisy} game is also PAC core-stable for the \emph{unknown noise-free} game. This prediction probability depends on the probability of a combinatorial construct called an ‘agreement event’. We explicitly obtain the agreement probability for $n$ agent noisy game with $l\geq 2$ support noise distribution. For a user-given satisfaction value on this probability, we identify the noise regimes for which an estimated partition is noise robust; that is, it is PAC core-stable in both the noisy and noise-free games. We obtain similar robustness results when the estimated partition is not PAC core-stable. These noise regimes correspond to the level sets of the agreement probability function and are non-convex sets. Moreover, an important fact is that the prediction probability can be high even if high noise values occur with a high probability. Further, for a class of top-responsive hedonic games, we obtain the bounds on the extra noisy samples required to get noise robustness with a user-given satisfaction value. We completely solve the noise robustness problem of a $2$ agent hedonic game. In particular, we obtain the prediction probability function for $l=2$ and $l=3$ noise support cases. For $l=2$, the prediction probability is convex in noise probability, but the noise robust regime is non-convex. Its minimum value, called the safety value, is 0.62; so, below 0.62, the noise robust regime is the entire probability simplex. However, for $l \geq 3$, the prediction probability is non-convex; so, the safety value is the global minima of a non-convex function and is computationally hard.' volume: 189 URL: https://proceedings.mlr.press/v189/trivedi23a.html PDF: https://proceedings.mlr.press/v189/trivedi23a/trivedi23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-trivedi23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Prashant family: Trivedi - given: Nandyala family: Hemachandra editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1038-1053 id: trivedi23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1038 lastpage: 1053 published: 2023-04-13 00:00:00 +0000 - title: 'On the expressivity of bi-Lipschitz normalizing flows' abstract: 'An invertible function is bi-Lipschitz if both the function and its inverse have bounded Lipschitz constants. Most state-of-the-art Normalizing Flows are bi-Lipschitz by design or by training to limit numerical errors (among other things). In this paper, we discuss the expressivity of bi-Lipschitz Normalizing Flows and identify several target distributions that are difficult to approximate using such models. Then, we characterize the expressivity of bi-Lipschitz Normalizing Flows by giving several lower bounds on the Total Variation distance between these particularly unfavorable distributions and their best possible approximation. Finally, we show how to use the bounds to adjust the training parameters, and discuss potential remedies.' volume: 189 URL: https://proceedings.mlr.press/v189/verine23a.html PDF: https://proceedings.mlr.press/v189/verine23a/verine23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-verine23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Alexandre family: Verine - given: Benjamin family: Negrevergne - given: Yann family: Chevaleyre - given: Fabrice family: Rossi editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1054-1069 id: verine23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1054 lastpage: 1069 published: 2023-04-13 00:00:00 +0000 - title: 'Constrained Contrastive Reinforcement Learning' abstract: 'Learning to control from complex observations remains a major challenge in the application of model-based reinforcement learning (MBRL). Existing MBRL methods apply contrastive learning to replace pixel-level reconstruction, improving the performance of the latent world model. However, previous contrastive learning approaches in MBRL fail to utilize task-relevant information, making it difficult to aggregate observations with the same task-relevant information but the different task-irrelevant information in latent space. In this work, we first propose Constrained Contrastive Reinforcement Learning (C2RL), an MBRL method that learns a world model through a combination of two contrastive losses based on latent dynamics and task-relevant state abstraction respectively, utilizing reward information to accelerate model learning. Then, we propose a hyperparameter $\beta$ to balance two kinds of contrastive losses to strengthen the representation ability of the latent dynamics. The experimental results show that our approach outperforms state-of-the-art methods in both the natural video and standard background setting on challenging DMControl tasks.' volume: 189 URL: https://proceedings.mlr.press/v189/wang23a.html PDF: https://proceedings.mlr.press/v189/wang23a/wang23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-wang23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Haoyu family: Wang - given: Xinrui family: Yang - given: Yuhang family: Wang - given: Lan family: Xuguang editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1070-1084 id: wang23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1070 lastpage: 1084 published: 2023-04-13 00:00:00 +0000 - title: 'Evaluating the perceived safety of urban city via maximum entropy deep inverse reinforcement learning' abstract: 'Inspired by expert evaluation policy for urban perception, we proposed a novel inverse reinforcement learning (IRL) based framework for predicting urban safety and recovering the corresponding reward function. We also presented a scalable state representation method to model the prediction problem as a Markov decision process (MDP) and use reinforcement learning (RL) to solve the problem. Additionally, we built a dataset called SmallCity based on the crowdsourcing method to conduct the research. As far as we know, this is the first time the IRL approach has been introduced to the urban safety perception and planning field to help experts quantitatively analyze perceptual features. Our results showed that IRL has promising prospects in this field. We will later open-source the crowdsourcing data collection site and the model proposed in this paper.' volume: 189 URL: https://proceedings.mlr.press/v189/wang23c.html PDF: https://proceedings.mlr.press/v189/wang23c/wang23c.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-wang23c.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Yaxuan family: Wang - given: Zhixin family: Zeng - given: Qijun family: Zhao editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1085-1100 id: wang23c issued: date-parts: - 2023 - 4 - 13 firstpage: 1085 lastpage: 1100 published: 2023-04-13 00:00:00 +0000 - title: 'Margin Calibration for Long-Tailed Visual Recognition' abstract: 'Long-tailed visual recognition tasks pose great challenges for neural networks on how to handle the imbalanced predictions between head (common) and tail (rare) classes, i.e., models tend to classify tail classes as head classes. While existing research focused on data resampling and loss function engineering, in this paper, we take a different perspective: the classification margins. We study the relationship between the margins and logits and empirically observe that the uncalibrated margins and logits are positively correlated. We propose a simple yet effective MARgin Calibration approach (MARC) to calibrate the margins to obtain better logits. We validate MARC through extensive experiments on common long-tailed benchmarks including CIFAR-LT, ImageNet-LT, Places-LT, and iNaturalist-LT. Experimental results demonstrate that our MARC achieves favorable results on these benchmarks. In addition, MARC is extremely easy to implement with just three lines of code. We hope this simple approach will motivate people to rethink the uncalibrated margins and logits in long-tailed visual recognition.' volume: 189 URL: https://proceedings.mlr.press/v189/wang23b.html PDF: https://proceedings.mlr.press/v189/wang23b/wang23b.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-wang23b.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Yidong family: Wang - given: Bowen family: Zhang - given: Wenxin family: Hou - given: Zhen family: Wu - given: Jindong family: Wang - given: Takahiro family: Shinozaki editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1101-1116 id: wang23b issued: date-parts: - 2023 - 4 - 13 firstpage: 1101 lastpage: 1116 published: 2023-04-13 00:00:00 +0000 - title: 'Layer-wise Adaptive Graph Convolution Networks Using Generalized Pagerank' abstract: ' We investigate adaptive layer-wise graph convolution in deep GCN models. We propose AdaGPR to learn generalized Pageranks at each layer of a GCNII network to induce adaptive convolution. We show that the generalization bound for AdaGPR is bounded by a polynomial of the eigenvalue spectrum of the normalized adjacency matrix in the order of the number of generalized Pagerank coefficients. By analysing the generalization bounds we show that oversmoothing depends on both the convolutions by the higher orders of the normalized adjacency matrix and the depth of the model. We performed evaluations on node-classification using benchmark real data and show that AdaGPR provides improved accuracies compared to existing graph convolution networks while demonstrating robustness against oversmoothing. Further, we demonstrate that analysis of coefficients of layer-wise generalized Pageranks allows us to qualitatively understand convolution at each layer enabling model interpretations.' volume: 189 URL: https://proceedings.mlr.press/v189/wimalawarne23a.html PDF: https://proceedings.mlr.press/v189/wimalawarne23a/wimalawarne23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-wimalawarne23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Kishan family: Wimalawarne - given: Taiji family: Suzuki editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1117-1132 id: wimalawarne23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1117 lastpage: 1132 published: 2023-04-13 00:00:00 +0000 - title: 'Pose Guided Human Image Synthesis with Partially Decoupled GAN' abstract: 'Pose Guided Human Image Synthesis (PGHIS) is a challenging task of transforming a human image from the reference pose to a target pose while preserving its style. Most existing methods encode the texture of the whole reference human image into a latent space, and then utilize a decoder to synthesize the image texture of the target pose. However, it is difficult to recover the detailed texture of the whole human image. To alleviate this problem, we propose a method by decoupling the human body into several parts (\emph{e.g.}, hair, face, hands, feet, \emph{etc.}) and then using each of these parts to guide the synthesis of a realistic image of the person, which preserves the detailed information of the generated images. In addition, we design a multi-head attention-based module for PGHIS. Because most convolutional neural network-based methods have difficulty in modeling long-range dependency due to the convolutional operation, the long-range modeling capability of attention mechanism is more suitable than convolutional neural networks for pose transfer task, especially for sharp pose deformation. Extensive experiments on Market-1501 and DeepFashion datasets reveal that our method almost outperforms other existing state-of-the-art methods in terms of both qualitative and quantitative metrics.' volume: 189 URL: https://proceedings.mlr.press/v189/wu23a.html PDF: https://proceedings.mlr.press/v189/wu23a/wu23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-wu23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Jianhan family: Wu - given: Shijing family: Si - given: Jianzong family: Wang - given: Xiaoyang family: Qu - given: Xiao family: Jing editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1133-1148 id: wu23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1133 lastpage: 1148 published: 2023-04-13 00:00:00 +0000 - title: 'Probabilistic Fusion of Neural Networks that Incorporates Global Information' abstract: 'As one of the approaches in Federated Learning, model fusion distills models trained on local clients into a global model. The previous method, Probabilistic Federated Neural Matching (PFNM), can match and fuse local neural networks with varying global model sizes and data heterogeneity using the Bayesian nonparametric framework. However, the alternating optimization process applied by PFNM causes absence of global neuron information. In this paper, we propose a new method that extends PFNM by introducing a Kullback-Leibler (KL) divergence penalty, so that it can exploit information in both local and global neurons. We show theoretically that the extended PFNM with a penalty derived from KL divergence can fix the drawback of PFNM by making a balance between Euclidean distance and the prior probability of neurons. Experiments on deep fully-connected as well as deep convolutional neural networks demonstrate that our new method outperforms popular state-of-the-art federated learning methods in both image classification and semantic segmentation tasks.' volume: 189 URL: https://proceedings.mlr.press/v189/xiao23b.html PDF: https://proceedings.mlr.press/v189/xiao23b/xiao23b.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-xiao23b.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Peng family: Xiao - given: Biao family: Zhang - given: Samuel family: Cheng - given: Ke family: Wei - given: Shuqin family: Zhang editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1149-1164 id: xiao23b issued: date-parts: - 2023 - 4 - 13 firstpage: 1149 lastpage: 1164 published: 2023-04-13 00:00:00 +0000 - title: 'Semantic Cross Attention for Few-shot Learning' abstract: 'Few-shot learning (FSL) has attracted considerable attention recently. Among existing approaches, the metric-based method aims to train an embedding network that can make similar samples close while dissimilar samples as far as possible and achieves promising results. FSL is characterized by using only a few images to train a model that can generalize to novel classes in image classification problems, but this setting makes it difficult to learn the visual features that can identify the images’ appearance variations. The model training is likely to move in the wrong direction, as the images in an identical semantic class may have dissimilar appearances, whereas the images in different semantic classes may share a similar appearance. We argue that FSL can benefit from additional semantic features to learn discriminative feature representations. Thus, this study proposes a multi-task learning approach to view semantic features of label text as an auxiliary task to help boost the performance of the FSL task. Our proposed model uses word-embedding representations as semantic features to help train the embedding network and a semantic cross-attention module to bridge the semantic features into the typical visual modal. The proposed approach is simple, but produces excellent results. We apply our proposed approach to two previous metric-based FSL methods, all of which can substantially improve performance. The source code for our model is accessible from github.' volume: 189 URL: https://proceedings.mlr.press/v189/xiao23a.html PDF: https://proceedings.mlr.press/v189/xiao23a/xiao23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-xiao23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Bin family: Xiao - given: Chien-Liang family: Liu - given: Wen-Hoar family: Hsaio editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1165-1180 id: xiao23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1165 lastpage: 1180 published: 2023-04-13 00:00:00 +0000 - title: 'An Enhanced Human Activity Recognition Algorithm with Positional Attention' abstract: 'Human activity recognition (HAR) attracts widespread attention from researchers recently, and deep learning is employed as a dominant paradigm of solving HAR problems. The previous techniques rely on domain knowledge or attention mechanism extract long-range dependency in temporal dimension and cross channel correlation in sensor’s channel dimension. In this paper, a HAR model with positional attention (PA), termed as PA-HAR, is presented. To enhance the features in both sensor’s channel and temporal dimensions, we propose to split the sensor signals into two 1D features to capture the long-range dependency along the temporal-axis and signal’s cross-channel information along the sensor’s channel-axis. Furthermore, we embed the features with positional information by encoding the generated features into pairs of temporal-aware and sensor’s channel-aware attention maps and weighting the input feature maps. Extensive experiments based on five public datasets demonstrate that the proposed PA-HAR algorithm achieves a competitive performance in HAR related tasks compared with the state-of-the-art approaches.' volume: 189 URL: https://proceedings.mlr.press/v189/xu23a.html PDF: https://proceedings.mlr.press/v189/xu23a/xu23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-xu23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Chenyang family: Xu - given: Jianfei family: Shen - given: Feiyi family: Fan - given: Tian family: Qiu - given: Zhihong family: Mao editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1181-1196 id: xu23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1181 lastpage: 1196 published: 2023-04-13 00:00:00 +0000 - title: 'Cross-Scale Context Extracted Hashing for Fine-Grained Image Binary Encoding' abstract: 'Deep hashing has been widely applied to large-scale image retrieval tasks owing to efficient computation and low storage cost by encoding high-dimensional image data into binary codes. Since binary codes do not contain as much information as float features, the essence of binary encoding is preserving the main context to guarantee retrieval quality. However, the existing hashing methods have great limitations on suppressing redundant background information and accurately encoding from Euclidean space to Hamming space by a simple sign function. In order to solve these problems, a Cross-Scale Context Extracted Hashing Network (CSCE-Net) is proposed in this paper. Firstly, we design a two-branch framework to capture fine-grained local information while maintaining high-level global semantic information. Besides, Attention guided Information Extraction module (AIE) is introduced between two branches, which suppresses areas of low context information cooperated with global sliding windows. Unlike previous methods, our CSCE-Net learns a content-related Dynamic Sign Function (DSF) to replace the original simple sign function. Therefore, the proposed CSCE-Net is context-sensitive and able to perform well on accurate image binary encoding. We further demonstrate that our CSCE-Net is superior to the existing hashing methods, which improves retrieval performance on standard benchmarks.' volume: 189 URL: https://proceedings.mlr.press/v189/xue23a.html PDF: https://proceedings.mlr.press/v189/xue23a/xue23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-xue23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Xuetong family: Xue - given: Jiaying family: Shi - given: Xinxue family: He - given: Shenghui family: Xu - given: Zhaoming family: Pan editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1197-1212 id: xue23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1197 lastpage: 1212 published: 2023-04-13 00:00:00 +0000 - title: 'Sliced Wasserstein variational inference' abstract: 'Variational Inference approximates an unnormalized distribution via the minimization of Kullback-Leibler (KL) divergence. Although this divergence is efficient for computation and has been widely used in applications, it suffers from some unreasonable properties. For example, it is not a proper metric, i.e., it is non-symmetric and does not preserve the triangle inequality. On the other hand, optimal transport distances recently have shown some advantages over KL divergence. With the help of these advantages, we propose a new variational inference method by minimizing sliced Wasserstein distance–a valid metric arising from optimal transport. This sliced Wasserstein distance can be approximated simply by running MCMC but without solving any optimization problem. Our approximation also does not require a tractable density function of variational distributions so that approximating families can be amortized by generators like neural networks. Furthermore, we provide an analysis of the theoretical properties of our method. Experiments on synthetic and real data are illustrated to show the performance of the proposed method.' volume: 189 URL: https://proceedings.mlr.press/v189/yi23a.html PDF: https://proceedings.mlr.press/v189/yi23a/yi23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-yi23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Mingxuan family: Yi - given: Song family: Liu editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1213-1228 id: yi23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1213 lastpage: 1228 published: 2023-04-13 00:00:00 +0000 - title: 'Learning with Interactive Models over Decision-Dependent Distributions' abstract: 'Classical supervised learning generally trains one model from an i.i.d. data according to an unknown yet fixed distribution. In some real applications such as finance, however, multiple models may be trained by different companies and interacted in a dynamic environment, where the data distribution may take shift according to different models’ decisions. In this work, we study two models for simplicity, and formalize such scenario as a learning problem of two models over decision-dependent distributions. We develop the Repeated Risk Minimization (RRM) for two models, and present a sufficient condition to the existence of stable points for RRM, that is, an equilibrium notion. We further provide the theoretical analysis for the convergence of RRM to stable points based on data distribution and finite training sample, respectively. We also study more practical algorithms, such as gradient descent and stochastic gradient descent, to solve the RRM problem with convergence guarantees and we finally present some empirical studies to validate our theoretical analysis.' volume: 189 URL: https://proceedings.mlr.press/v189/yuan23a.html PDF: https://proceedings.mlr.press/v189/yuan23a/yuan23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-yuan23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Man-Jie family: Yuan - given: Wei family: Gao editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1229-1244 id: yuan23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1229 lastpage: 1244 published: 2023-04-13 00:00:00 +0000 - title: 'Constrained Density Matching and Modeling for Cross-lingual Alignment of Contextualized Representations' abstract: 'Multilingual representations pre-trained with monolingual data exhibit considerably unequal task performances across languages. Previous studies address this challenge with resource-intensive contextualized alignment, which assumes the availability of large parallel data, thereby leaving under-represented language communities behind. In this work, we attribute the data hungriness of previous alignment techniques to two limitations: (i) the inability to sufficiently leverage data and (ii) these techniques are not trained properly. To address these issues, we introduce supervised and unsupervised density-based approaches named Real-NVP and GAN-Real-NVP, driven by Normalizing Flow, to perform alignment, both dissecting the alignment of multilingual subspaces into density matching and density modeling. We complement these approaches with our validation criteria in order to guide the training process. Our experiments encompass 16 alignments, including our approaches, evaluated across 6 language pairs, synthetic data and 5 NLP tasks. We demonstrate the effectiveness of our approaches in the scenarios of limited and no parallel data. First, our supervised approach trained on 20k parallel data (sentences) mostly surpasses Joint-Align and InfoXLM trained on over 100k parallel sentences. Second, parallel data can be removed without sacrificing performance when integrating our unsupervised approach in our bootstrapping procedure, which is theoretically motivated to enforce equality of multilingual subspaces. Moreover, we demonstrate the advantages of validation criteria over validation data for guiding supervised training.' volume: 189 URL: https://proceedings.mlr.press/v189/zhao23a.html PDF: https://proceedings.mlr.press/v189/zhao23a/zhao23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-zhao23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Wei family: Zhao - given: Steffen family: Eger editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1245-1260 id: zhao23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1245 lastpage: 1260 published: 2023-04-13 00:00:00 +0000 - title: 'EENAS: An Efficient Evolutionary Algorithm for Neural Architecture Search' abstract: 'Neural Architecture Search (NAS) has been widely applied to automatic neural architecture design. Traditional NAS methods often evaluate a large number of architectures, leading to expensive computation overhead. To speed-up architecture search, recent NAS methods try to employ network estimation strategies for guidance of promising architecture selection. In this paper, we have proposed an efficient evolutionary algorithm for NAS, which adapts the most advanced proxy of synthetic signal bases for architecture estimation. Extensive experiments show that our method outperforms state-of-the-art NAS methods, on NAS-Bench-101 search space and NAS-Bench-201 search space (CIFAR-10, CIFAR-100 and ImageNet16-120). Compared with existing works, our method could identify better architectures with greatly reduced search time.' volume: 189 URL: https://proceedings.mlr.press/v189/jian23a.html PDF: https://proceedings.mlr.press/v189/jian23a/jian23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-jian23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Zheng family: Jian - given: Han family: Wenran - given: Zhang family: Ying - given: Ji family: Shufan editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1261-1276 id: jian23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1261 lastpage: 1276 published: 2023-04-13 00:00:00 +0000 - title: 'A Novel Differentiable Mixed-Precision Quantization Search Framework for Alleviating the Matthew Effect and Improving Robustness' abstract: 'Network quantization is an effective and widely-used model compression technique. Recently, several works apply differentiable neural architectural search (NAS) methods to mixed-precision quantization (MPQ) and achieve encouraging results. However, the nature of differentiable architecture search can lead to the Matthew Effect in the mixed-precision. The candidates with higher bit-widths would be trained maturely earlier while the candidates with lower bit-widths may never have the chance to express the desired function. To address this issue, we propose a novel mixed-precision quantization framework. The mixed-precision search is resolved as a distribution learning problem, which alleviates the Matthew effect and improves the generalization ability. Meanwhile, different from generic differentiable NAS methods, search space will grow rapidly as the depth of the network increases in the mixed-precision quantization search. This makes the supernet harder to train and the search process unstable. To this end, we add a skip connection with a gradually decreasing architecture weight between convolutional layers in the supernet to improve robustness. The skip connection will help the optimization of the search process and will not participate in the bit width competition. Extensive experiments on CIFAR-10 and ImageNet demonstrate the effectiveness of the proposed methods. For example, when quantizing ResNet-50 on ImageNet, we achieve a state-of-the-art 156.10x Bitops compression rate while maintaining a 75.87$%$ accuracy.' volume: 189 URL: https://proceedings.mlr.press/v189/zhou23a.html PDF: https://proceedings.mlr.press/v189/zhou23a/zhou23a.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-zhou23a.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Hengyi family: Zhou - given: Hongyi family: He - given: Wanchen family: Liu - given: Yuhai family: Li - given: Haonan family: Zhang - given: Longjun family: Liu editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1277-1292 id: zhou23a issued: date-parts: - 2023 - 4 - 13 firstpage: 1277 lastpage: 1292 published: 2023-04-13 00:00:00 +0000 - title: 'Multi-scale Progressive Gated Transformer for Physiological Signal Classification' abstract: 'Physiological signal classification is of great significance for health monitoring and medical diagnosis. Deep learning-based methods (e.g. RNN and CNN) have been used in this domain to obtain reliable predictions. However, the performance of existing methods is constrained by the long-term dependence and irregular vibration of the univariate physiological signal sequence. To overcome these limitations, this paper proposes a Multi-scale Progressive Gated Transformer (MPGT) model to learn multi-scale temporal representations for better physiological signal classification. The key novelties of MPGT are the proposed Multi-scale Temporal Feature extraction (MTF) and Progressive Gated Transformer (PGT). The former adopts coarse- and fine-grained feature extractors to project the input signal data into different temporal granularity embedding spaces and the latter integrates such multi-scale information for data representation. Classification task is then conducted on the learned representations. Experimental results on real-world datasets demonstrate the superiority of the proposed model.' volume: 189 URL: https://proceedings.mlr.press/v189/zhou23b.html PDF: https://proceedings.mlr.press/v189/zhou23b/zhou23b.pdf edit: https://github.com/mlresearch//v189/edit/gh-pages/_posts/2023-04-13-zhou23b.md series: 'Proceedings of Machine Learning Research' container-title: 'Proceedings of The 14th Asian Conference on Machine Learning' publisher: 'PMLR' author: - given: Wei family: Zhou - given: Hao family: Wang - given: Yiling family: Zhang - given: Cheng family: Long - given: Yan family: Yang - given: Dongjie family: Wang editor: - given: Emtiyaz family: Khan - given: Mehmet family: Gonen page: 1293-1308 id: zhou23b issued: date-parts: - 2023 - 4 - 13 firstpage: 1293 lastpage: 1308 published: 2023-04-13 00:00:00 +0000