RoLNiP: Robust Learning Using Noisy Pairwise Comparisons

Samartha S. Maheshwara, Naresh Manwani
Proceedings of The 14th Asian Conference on Machine Learning, PMLR 189:706-721, 2023.

Abstract

This paper presents a robust approach for learning from noisy pairwise comparisons. We propose sufficient conditions on the loss function under which the risk minimization frame- work becomes robust to noise in the pairwise similar dissimilar data. Our approach does not require the knowledge of noise rate in the uniform noise case. In the case of conditional noise, the proposed method depends on the noise rates. For such cases, we offer a provably correct approach for estimating the noise rates. Thus, we propose an end-to-end approach to learning robust classifiers in this setting. We experimentally show that the proposed approach RoLNiP outperforms the robust state-of-the-art methods for learning with noisy pairwise comparisons.

Cite this Paper

BibTeX
@InProceedings{pmlr-v189-maheshwara23a, title = {RoLNiP: Robust Learning Using Noisy Pairwise Comparisons}, author = {Maheshwara, Samartha S. and Manwani, Naresh}, booktitle = {Proceedings of The 14th Asian Conference on Machine Learning}, pages = {706--721}, year = {2023}, editor = {Khan, Emtiyaz and Gonen, Mehmet}, volume = {189}, series = {Proceedings of Machine Learning Research}, month = {12--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v189/maheshwara23a/maheshwara23a.pdf}, url = {https://proceedings.mlr.press/v189/maheshwara23a.html}, abstract = {This paper presents a robust approach for learning from noisy pairwise comparisons. We propose sufficient conditions on the loss function under which the risk minimization frame- work becomes robust to noise in the pairwise similar dissimilar data. Our approach does not require the knowledge of noise rate in the uniform noise case. In the case of conditional noise, the proposed method depends on the noise rates. For such cases, we offer a provably correct approach for estimating the noise rates. Thus, we propose an end-to-end approach to learning robust classifiers in this setting. We experimentally show that the proposed approach RoLNiP outperforms the robust state-of-the-art methods for learning with noisy pairwise comparisons.} }
Endnote
%0 Conference Paper %T RoLNiP: Robust Learning Using Noisy Pairwise Comparisons %A Samartha S. Maheshwara %A Naresh Manwani %B Proceedings of The 14th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Emtiyaz Khan %E Mehmet Gonen %F pmlr-v189-maheshwara23a %I PMLR %P 706--721 %U https://proceedings.mlr.press/v189/maheshwara23a.html %V 189 %X This paper presents a robust approach for learning from noisy pairwise comparisons. We propose sufficient conditions on the loss function under which the risk minimization frame- work becomes robust to noise in the pairwise similar dissimilar data. Our approach does not require the knowledge of noise rate in the uniform noise case. In the case of conditional noise, the proposed method depends on the noise rates. For such cases, we offer a provably correct approach for estimating the noise rates. Thus, we propose an end-to-end approach to learning robust classifiers in this setting. We experimentally show that the proposed approach RoLNiP outperforms the robust state-of-the-art methods for learning with noisy pairwise comparisons.
APA
Maheshwara, S.S. & Manwani, N.. (2023). RoLNiP: Robust Learning Using Noisy Pairwise Comparisons. Proceedings of The 14th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 189:706-721 Available from https://proceedings.mlr.press/v189/maheshwara23a.html.

Related Material