Progressive Identification of True Labels for Partial-Label Learning

Jiaqi Lv, Miao Xu, Lei Feng, Gang Niu, Xin Geng, Masashi Sugiyama
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:6500-6510, 2020.

Abstract

Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed learning objectives as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data. The goal of this paper is to propose a novel framework of PLL with flexibility on the model and optimization algorithm. More specifically, we propose a novel estimator of the classification risk, theoretically analyze the classifier-consistency, and establish an estimation error bound. Then we propose a progressive identification algorithm for approximately minimizing the proposed risk estimator, where the update of the model and identification of true labels are conducted in a seamless manner. The resulting algorithm is model-independent and loss-independent, and compatible with stochastic optimization. Thorough experiments demonstrate it sets the new state of the art.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-lv20a, title = {Progressive Identification of True Labels for Partial-Label Learning}, author = {Lv, Jiaqi and Xu, Miao and Feng, Lei and Niu, Gang and Geng, Xin and Sugiyama, Masashi}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {6500--6510}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/lv20a/lv20a.pdf}, url = {https://proceedings.mlr.press/v119/lv20a.html}, abstract = {Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed learning objectives as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data. The goal of this paper is to propose a novel framework of PLL with flexibility on the model and optimization algorithm. More specifically, we propose a novel estimator of the classification risk, theoretically analyze the classifier-consistency, and establish an estimation error bound. Then we propose a progressive identification algorithm for approximately minimizing the proposed risk estimator, where the update of the model and identification of true labels are conducted in a seamless manner. The resulting algorithm is model-independent and loss-independent, and compatible with stochastic optimization. Thorough experiments demonstrate it sets the new state of the art.} }
Endnote
%0 Conference Paper %T Progressive Identification of True Labels for Partial-Label Learning %A Jiaqi Lv %A Miao Xu %A Lei Feng %A Gang Niu %A Xin Geng %A Masashi Sugiyama %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-lv20a %I PMLR %P 6500--6510 %U https://proceedings.mlr.press/v119/lv20a.html %V 119 %X Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed learning objectives as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data. The goal of this paper is to propose a novel framework of PLL with flexibility on the model and optimization algorithm. More specifically, we propose a novel estimator of the classification risk, theoretically analyze the classifier-consistency, and establish an estimation error bound. Then we propose a progressive identification algorithm for approximately minimizing the proposed risk estimator, where the update of the model and identification of true labels are conducted in a seamless manner. The resulting algorithm is model-independent and loss-independent, and compatible with stochastic optimization. Thorough experiments demonstrate it sets the new state of the art.
APA
Lv, J., Xu, M., Feng, L., Niu, G., Geng, X. & Sugiyama, M.. (2020). Progressive Identification of True Labels for Partial-Label Learning. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:6500-6510 Available from https://proceedings.mlr.press/v119/lv20a.html.

Related Material