Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy

Ke Sun, Bing Yu, Zhouchen Lin, Zhanxing Zhu
Proceedings of the 15th Asian Conference on Machine Learning, PMLR 222:1276-1291, 2024.

Abstract

Regularization plays a crucial role in machine learning models, especially for deep neural networks. The existing regularization techniques mainly rely on the i.i.d. assumption and only consider the knowledge from the current sample, without the leverage of the neighboring relationship between samples. In this work, we propose a general regularizer called \textbf{Patch-level Neighborhood Interpolation (Pani)} that conducts a non-local representation in the computation of networks. Our proposal explicitly constructs patch-level graphs in different layers and then linearly interpolates neighborhood patch features, serving as a general and effective regularization strategy. Further, we customize our approach into two kinds of popular regularization methods, namely Virtual Adversarial Training (VAT) and MixUp as well as its variants. The first derived \textbf{Pani VAT} presents a novel way to construct non-local adversarial smoothness by employing patch-level interpolated perturbations. The second derived \textbf{Pani MixUp} method extends the MixUp, and achieves superiority over MixUp and competitive performance over state-of-the-art variants of MixUp method with a significant advantage in computational efficiency. Extensive experiments have verified the effectiveness of our Pani approach in both supervised and semi-supervised settings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v222-sun24a, title = {Patch-level Neighborhood Interpolation: {A} General and Effective Graph-based Regularization Strategy}, author = {Sun, Ke and Yu, Bing and Lin, Zhouchen and Zhu, Zhanxing}, booktitle = {Proceedings of the 15th Asian Conference on Machine Learning}, pages = {1276--1291}, year = {2024}, editor = {Yanıkoğlu, Berrin and Buntine, Wray}, volume = {222}, series = {Proceedings of Machine Learning Research}, month = {11--14 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v222/sun24a/sun24a.pdf}, url = {https://proceedings.mlr.press/v222/sun24a.html}, abstract = {Regularization plays a crucial role in machine learning models, especially for deep neural networks. The existing regularization techniques mainly rely on the i.i.d. assumption and only consider the knowledge from the current sample, without the leverage of the neighboring relationship between samples. In this work, we propose a general regularizer called \textbf{Patch-level Neighborhood Interpolation (Pani)} that conducts a non-local representation in the computation of networks. Our proposal explicitly constructs patch-level graphs in different layers and then linearly interpolates neighborhood patch features, serving as a general and effective regularization strategy. Further, we customize our approach into two kinds of popular regularization methods, namely Virtual Adversarial Training (VAT) and MixUp as well as its variants. The first derived \textbf{Pani VAT} presents a novel way to construct non-local adversarial smoothness by employing patch-level interpolated perturbations. The second derived \textbf{Pani MixUp} method extends the MixUp, and achieves superiority over MixUp and competitive performance over state-of-the-art variants of MixUp method with a significant advantage in computational efficiency. Extensive experiments have verified the effectiveness of our Pani approach in both supervised and semi-supervised settings.} }
Endnote
%0 Conference Paper %T Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy %A Ke Sun %A Bing Yu %A Zhouchen Lin %A Zhanxing Zhu %B Proceedings of the 15th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Berrin Yanıkoğlu %E Wray Buntine %F pmlr-v222-sun24a %I PMLR %P 1276--1291 %U https://proceedings.mlr.press/v222/sun24a.html %V 222 %X Regularization plays a crucial role in machine learning models, especially for deep neural networks. The existing regularization techniques mainly rely on the i.i.d. assumption and only consider the knowledge from the current sample, without the leverage of the neighboring relationship between samples. In this work, we propose a general regularizer called \textbf{Patch-level Neighborhood Interpolation (Pani)} that conducts a non-local representation in the computation of networks. Our proposal explicitly constructs patch-level graphs in different layers and then linearly interpolates neighborhood patch features, serving as a general and effective regularization strategy. Further, we customize our approach into two kinds of popular regularization methods, namely Virtual Adversarial Training (VAT) and MixUp as well as its variants. The first derived \textbf{Pani VAT} presents a novel way to construct non-local adversarial smoothness by employing patch-level interpolated perturbations. The second derived \textbf{Pani MixUp} method extends the MixUp, and achieves superiority over MixUp and competitive performance over state-of-the-art variants of MixUp method with a significant advantage in computational efficiency. Extensive experiments have verified the effectiveness of our Pani approach in both supervised and semi-supervised settings.
APA
Sun, K., Yu, B., Lin, Z. & Zhu, Z.. (2024). Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy. Proceedings of the 15th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 222:1276-1291 Available from https://proceedings.mlr.press/v222/sun24a.html.

Related Material