OTMatch: Improving Semi-Supervised Learning with Optimal Transport

Zhiquan Tan, Kaipeng Zheng, Weiran Huang
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47667-47680, 2024.

Abstract

Semi-supervised learning has made remarkable strides by effectively utilizing a limited amount of labeled data while capitalizing on the abundant information present in unlabeled data. However, current algorithms often prioritize aligning image predictions with specific classes generated through self-training techniques, thereby neglecting the inherent relationships that exist within these classes. In this paper, we present a new approach called OTMatch, which leverages semantic relationships among classes by employing an optimal transport loss function to match distributions. We conduct experiments on many standard vision and language datasets. The empirical results show improvements in our method above baseline, this demonstrates the effectiveness and superiority of our approach in harnessing semantic relationships to enhance learning performance in a semi-supervised setting.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-tan24f, title = {{OTM}atch: Improving Semi-Supervised Learning with Optimal Transport}, author = {Tan, Zhiquan and Zheng, Kaipeng and Huang, Weiran}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {47667--47680}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/tan24f/tan24f.pdf}, url = {https://proceedings.mlr.press/v235/tan24f.html}, abstract = {Semi-supervised learning has made remarkable strides by effectively utilizing a limited amount of labeled data while capitalizing on the abundant information present in unlabeled data. However, current algorithms often prioritize aligning image predictions with specific classes generated through self-training techniques, thereby neglecting the inherent relationships that exist within these classes. In this paper, we present a new approach called OTMatch, which leverages semantic relationships among classes by employing an optimal transport loss function to match distributions. We conduct experiments on many standard vision and language datasets. The empirical results show improvements in our method above baseline, this demonstrates the effectiveness and superiority of our approach in harnessing semantic relationships to enhance learning performance in a semi-supervised setting.} }
Endnote
%0 Conference Paper %T OTMatch: Improving Semi-Supervised Learning with Optimal Transport %A Zhiquan Tan %A Kaipeng Zheng %A Weiran Huang %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-tan24f %I PMLR %P 47667--47680 %U https://proceedings.mlr.press/v235/tan24f.html %V 235 %X Semi-supervised learning has made remarkable strides by effectively utilizing a limited amount of labeled data while capitalizing on the abundant information present in unlabeled data. However, current algorithms often prioritize aligning image predictions with specific classes generated through self-training techniques, thereby neglecting the inherent relationships that exist within these classes. In this paper, we present a new approach called OTMatch, which leverages semantic relationships among classes by employing an optimal transport loss function to match distributions. We conduct experiments on many standard vision and language datasets. The empirical results show improvements in our method above baseline, this demonstrates the effectiveness and superiority of our approach in harnessing semantic relationships to enhance learning performance in a semi-supervised setting.
APA
Tan, Z., Zheng, K. & Huang, W.. (2024). OTMatch: Improving Semi-Supervised Learning with Optimal Transport. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:47667-47680 Available from https://proceedings.mlr.press/v235/tan24f.html.

Related Material