Collaborative Classification from Noisy Labels

Lucas Maystre, Nagarjuna Kumarappan, Judith Bütepage, Mounia Lalmas
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:1639-1647, 2021.

Abstract

We consider a setting where users interact with a collection of N items on an online platform. We are given class labels possibly corrupted by noise, and we seek to recover the true class of each item. We postulate a simple probabilistic model of the interactions between users and items, based on the assumption that users interact with classes in different proportions. We then develop a message-passing algorithm that decodes the noisy class labels efficiently. Under suitable assumptions, our method provably recovers all items’ true classes in the large N limit, even when the interaction graph remains sparse. Empirically, we show that our approach is effective on several practical applications, including predicting the location of businesses, the category of consumer goods, and the language of audio content.

Cite this Paper

BibTeX
@InProceedings{pmlr-v130-maystre21a, title = { Collaborative Classification from Noisy Labels }, author = {Maystre, Lucas and Kumarappan, Nagarjuna and B{\"u}tepage, Judith and Lalmas, Mounia}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {1639--1647}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/maystre21a/maystre21a.pdf}, url = {https://proceedings.mlr.press/v130/maystre21a.html}, abstract = { We consider a setting where users interact with a collection of N items on an online platform. We are given class labels possibly corrupted by noise, and we seek to recover the true class of each item. We postulate a simple probabilistic model of the interactions between users and items, based on the assumption that users interact with classes in different proportions. We then develop a message-passing algorithm that decodes the noisy class labels efficiently. Under suitable assumptions, our method provably recovers all items’ true classes in the large N limit, even when the interaction graph remains sparse. Empirically, we show that our approach is effective on several practical applications, including predicting the location of businesses, the category of consumer goods, and the language of audio content. } }
Endnote
%0 Conference Paper %T Collaborative Classification from Noisy Labels %A Lucas Maystre %A Nagarjuna Kumarappan %A Judith Bütepage %A Mounia Lalmas %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-maystre21a %I PMLR %P 1639--1647 %U https://proceedings.mlr.press/v130/maystre21a.html %V 130 %X We consider a setting where users interact with a collection of N items on an online platform. We are given class labels possibly corrupted by noise, and we seek to recover the true class of each item. We postulate a simple probabilistic model of the interactions between users and items, based on the assumption that users interact with classes in different proportions. We then develop a message-passing algorithm that decodes the noisy class labels efficiently. Under suitable assumptions, our method provably recovers all items’ true classes in the large N limit, even when the interaction graph remains sparse. Empirically, we show that our approach is effective on several practical applications, including predicting the location of businesses, the category of consumer goods, and the language of audio content.
APA
Maystre, L., Kumarappan, N., Bütepage, J. & Lalmas, M.. (2021). Collaborative Classification from Noisy Labels . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:1639-1647 Available from https://proceedings.mlr.press/v130/maystre21a.html.

Related Material