Classification with Rejection Based on Cost-sensitive Classification

Nontawat Charoenphakdee, Zhenghang Cui, Yivan Zhang, Masashi Sugiyama
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1507-1517, 2021.

Abstract

The goal of classification with rejection is to avoid risky misclassification in error-critical applications such as medical diagnosis and product inspection. In this paper, based on the relationship between classification with rejection and cost-sensitive classification, we propose a novel method of classification with rejection by learning an ensemble of cost-sensitive classifiers, which satisfies all the following properties: (i) it can avoid estimating class-posterior probabilities, resulting in improved classification accuracy. (ii) it allows a flexible choice of losses including non-convex ones, (iii) it does not require complicated modifications when using different losses, (iv) it is applicable to both binary and multiclass cases, and (v) it is theoretically justifiable for any classification-calibrated loss. Experimental results demonstrate the usefulness of our proposed approach in clean-labeled, noisy-labeled, and positive-unlabeled classification.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-charoenphakdee21a, title = {Classification with Rejection Based on Cost-sensitive Classification}, author = {Charoenphakdee, Nontawat and Cui, Zhenghang and Zhang, Yivan and Sugiyama, Masashi}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {1507--1517}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/charoenphakdee21a/charoenphakdee21a.pdf}, url = {https://proceedings.mlr.press/v139/charoenphakdee21a.html}, abstract = {The goal of classification with rejection is to avoid risky misclassification in error-critical applications such as medical diagnosis and product inspection. In this paper, based on the relationship between classification with rejection and cost-sensitive classification, we propose a novel method of classification with rejection by learning an ensemble of cost-sensitive classifiers, which satisfies all the following properties: (i) it can avoid estimating class-posterior probabilities, resulting in improved classification accuracy. (ii) it allows a flexible choice of losses including non-convex ones, (iii) it does not require complicated modifications when using different losses, (iv) it is applicable to both binary and multiclass cases, and (v) it is theoretically justifiable for any classification-calibrated loss. Experimental results demonstrate the usefulness of our proposed approach in clean-labeled, noisy-labeled, and positive-unlabeled classification.} }
Endnote
%0 Conference Paper %T Classification with Rejection Based on Cost-sensitive Classification %A Nontawat Charoenphakdee %A Zhenghang Cui %A Yivan Zhang %A Masashi Sugiyama %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-charoenphakdee21a %I PMLR %P 1507--1517 %U https://proceedings.mlr.press/v139/charoenphakdee21a.html %V 139 %X The goal of classification with rejection is to avoid risky misclassification in error-critical applications such as medical diagnosis and product inspection. In this paper, based on the relationship between classification with rejection and cost-sensitive classification, we propose a novel method of classification with rejection by learning an ensemble of cost-sensitive classifiers, which satisfies all the following properties: (i) it can avoid estimating class-posterior probabilities, resulting in improved classification accuracy. (ii) it allows a flexible choice of losses including non-convex ones, (iii) it does not require complicated modifications when using different losses, (iv) it is applicable to both binary and multiclass cases, and (v) it is theoretically justifiable for any classification-calibrated loss. Experimental results demonstrate the usefulness of our proposed approach in clean-labeled, noisy-labeled, and positive-unlabeled classification.
APA
Charoenphakdee, N., Cui, Z., Zhang, Y. & Sugiyama, M.. (2021). Classification with Rejection Based on Cost-sensitive Classification. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:1507-1517 Available from https://proceedings.mlr.press/v139/charoenphakdee21a.html.

Related Material