Bridging Ordinary-Label Learning and Complementary-Label Learning

Yasuhiro Katsura, Masato Uchida
Proceedings of The 12th Asian Conference on Machine Learning, PMLR 129:161-176, 2020.

Abstract

A supervised learning framework has been proposed for the situation where each trainingdata is provided with a complementary label that represents a class to which the pattern does not belong. In the existing literature, complementary-label learning has been studied independently from ordinary-label learning, which assumes that each training data is provided with a label representing the class to which the pattern belongs. However, providing a complementary label should be treated as equivalent to providing the rest of all the labels as the candidates of the one true class. In this paper, we focus on the fact that the loss functions for one-versus-all and pairwise classification corresponding to ordinary-label learning and complementary-label learning satisfy certain additivity and duality, and provide a framework which directly bridge those existing supervised learning frameworks. Further, we derive classification risk and error bound for any loss functions which satisfy additivity and duality.

Cite this Paper

BibTeX
@InProceedings{pmlr-v129-katsura20a, title = {Bridging Ordinary-Label Learning and Complementary-Label Learning}, author = {Katsura, Yasuhiro and Uchida, Masato}, booktitle = {Proceedings of The 12th Asian Conference on Machine Learning}, pages = {161--176}, year = {2020}, editor = {Pan, Sinno Jialin and Sugiyama, Masashi}, volume = {129}, series = {Proceedings of Machine Learning Research}, month = {18--20 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v129/katsura20a/katsura20a.pdf}, url = {https://proceedings.mlr.press/v129/katsura20a.html}, abstract = {A supervised learning framework has been proposed for the situation where each trainingdata is provided with a complementary label that represents a class to which the pattern does not belong. In the existing literature, complementary-label learning has been studied independently from ordinary-label learning, which assumes that each training data is provided with a label representing the class to which the pattern belongs. However, providing a complementary label should be treated as equivalent to providing the rest of all the labels as the candidates of the one true class. In this paper, we focus on the fact that the loss functions for one-versus-all and pairwise classification corresponding to ordinary-label learning and complementary-label learning satisfy certain additivity and duality, and provide a framework which directly bridge those existing supervised learning frameworks. Further, we derive classification risk and error bound for any loss functions which satisfy additivity and duality.} }
Endnote
%0 Conference Paper %T Bridging Ordinary-Label Learning and Complementary-Label Learning %A Yasuhiro Katsura %A Masato Uchida %B Proceedings of The 12th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Sinno Jialin Pan %E Masashi Sugiyama %F pmlr-v129-katsura20a %I PMLR %P 161--176 %U https://proceedings.mlr.press/v129/katsura20a.html %V 129 %X A supervised learning framework has been proposed for the situation where each trainingdata is provided with a complementary label that represents a class to which the pattern does not belong. In the existing literature, complementary-label learning has been studied independently from ordinary-label learning, which assumes that each training data is provided with a label representing the class to which the pattern belongs. However, providing a complementary label should be treated as equivalent to providing the rest of all the labels as the candidates of the one true class. In this paper, we focus on the fact that the loss functions for one-versus-all and pairwise classification corresponding to ordinary-label learning and complementary-label learning satisfy certain additivity and duality, and provide a framework which directly bridge those existing supervised learning frameworks. Further, we derive classification risk and error bound for any loss functions which satisfy additivity and duality.
APA
Katsura, Y. & Uchida, M.. (2020). Bridging Ordinary-Label Learning and Complementary-Label Learning. Proceedings of The 12th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 129:161-176 Available from https://proceedings.mlr.press/v129/katsura20a.html.

Related Material