Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical

Wei Wang, Takashi Ishida, Yu-Jie Zhang, Gang Niu, Masashi Sugiyama
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50683-50710, 2024.

Abstract

Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches have relied on the uniform distribution assumption to model the generation of complementary labels, or on an ordinary-label training set to estimate the transition matrix in non-uniform cases. However, either condition may not be satisfied in real-world scenarios. In this paper, we propose a novel consistent approach that does not rely on these conditions. Inspired by the positive-unlabeled (PU) learning literature, we propose an unbiased risk estimator based on the Selected-Completely-at-Random assumption for complementary-label learning. We then introduce a risk-correction approach to address overfitting problems. Furthermore, we find that complementary-label learning can be expressed as a set of negative-unlabeled binary classification problems when using the one-versus-rest strategy. Extensive experimental results on both synthetic and real-world benchmark datasets validate the superiority of our proposed approach over state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-wang24ac, title = {Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical}, author = {Wang, Wei and Ishida, Takashi and Zhang, Yu-Jie and Niu, Gang and Sugiyama, Masashi}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {50683--50710}, 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/wang24ac/wang24ac.pdf}, url = {https://proceedings.mlr.press/v235/wang24ac.html}, abstract = {Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches have relied on the uniform distribution assumption to model the generation of complementary labels, or on an ordinary-label training set to estimate the transition matrix in non-uniform cases. However, either condition may not be satisfied in real-world scenarios. In this paper, we propose a novel consistent approach that does not rely on these conditions. Inspired by the positive-unlabeled (PU) learning literature, we propose an unbiased risk estimator based on the Selected-Completely-at-Random assumption for complementary-label learning. We then introduce a risk-correction approach to address overfitting problems. Furthermore, we find that complementary-label learning can be expressed as a set of negative-unlabeled binary classification problems when using the one-versus-rest strategy. Extensive experimental results on both synthetic and real-world benchmark datasets validate the superiority of our proposed approach over state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical %A Wei Wang %A Takashi Ishida %A Yu-Jie Zhang %A Gang Niu %A Masashi Sugiyama %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-wang24ac %I PMLR %P 50683--50710 %U https://proceedings.mlr.press/v235/wang24ac.html %V 235 %X Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches have relied on the uniform distribution assumption to model the generation of complementary labels, or on an ordinary-label training set to estimate the transition matrix in non-uniform cases. However, either condition may not be satisfied in real-world scenarios. In this paper, we propose a novel consistent approach that does not rely on these conditions. Inspired by the positive-unlabeled (PU) learning literature, we propose an unbiased risk estimator based on the Selected-Completely-at-Random assumption for complementary-label learning. We then introduce a risk-correction approach to address overfitting problems. Furthermore, we find that complementary-label learning can be expressed as a set of negative-unlabeled binary classification problems when using the one-versus-rest strategy. Extensive experimental results on both synthetic and real-world benchmark datasets validate the superiority of our proposed approach over state-of-the-art methods.
APA
Wang, W., Ishida, T., Zhang, Y., Niu, G. & Sugiyama, M.. (2024). Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:50683-50710 Available from https://proceedings.mlr.press/v235/wang24ac.html.

Related Material