Disparate Conditional Prediction in Multiclass Classifiers

Sivan Sabato, Eran Treister, Elad Yom-Tov
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52508-52525, 2025.

Abstract

We propose methods for auditing multiclass classifiers for fairness under multiclass equalized odds, by estimating the deviation from equalized odds when the classifier is not completely fair. We generalize to multiclass classifiers the measure of Disparate Conditional Prediction (DCP), originally suggested by Sabato & Yom-Tov (2020) for binary classifiers. DCP is defined as the fraction of the population for which the classifier predicts with conditional prediction probabilities that differ from the closest common baseline. We provide new local-optimization methods for estimating the multiclass DCP under two different regimes, one in which the conditional confusion matrices for each protected sub-population are known, and one in which these cannot be estimated, for instance, because the classifier is inaccessible or because good-quality individual-level data is not available. These methods can be used to detect classifiers that likely treat a significant fraction of the population unfairly. Experiments demonstrate the accuracy of the methods. The code for the experiments is provided as supplementary material.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-sabato25a, title = {Disparate Conditional Prediction in Multiclass Classifiers}, author = {Sabato, Sivan and Treister, Eran and Yom-Tov, Elad}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {52508--52525}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/sabato25a/sabato25a.pdf}, url = {https://proceedings.mlr.press/v267/sabato25a.html}, abstract = {We propose methods for auditing multiclass classifiers for fairness under multiclass equalized odds, by estimating the deviation from equalized odds when the classifier is not completely fair. We generalize to multiclass classifiers the measure of Disparate Conditional Prediction (DCP), originally suggested by Sabato & Yom-Tov (2020) for binary classifiers. DCP is defined as the fraction of the population for which the classifier predicts with conditional prediction probabilities that differ from the closest common baseline. We provide new local-optimization methods for estimating the multiclass DCP under two different regimes, one in which the conditional confusion matrices for each protected sub-population are known, and one in which these cannot be estimated, for instance, because the classifier is inaccessible or because good-quality individual-level data is not available. These methods can be used to detect classifiers that likely treat a significant fraction of the population unfairly. Experiments demonstrate the accuracy of the methods. The code for the experiments is provided as supplementary material.} }
Endnote
%0 Conference Paper %T Disparate Conditional Prediction in Multiclass Classifiers %A Sivan Sabato %A Eran Treister %A Elad Yom-Tov %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-sabato25a %I PMLR %P 52508--52525 %U https://proceedings.mlr.press/v267/sabato25a.html %V 267 %X We propose methods for auditing multiclass classifiers for fairness under multiclass equalized odds, by estimating the deviation from equalized odds when the classifier is not completely fair. We generalize to multiclass classifiers the measure of Disparate Conditional Prediction (DCP), originally suggested by Sabato & Yom-Tov (2020) for binary classifiers. DCP is defined as the fraction of the population for which the classifier predicts with conditional prediction probabilities that differ from the closest common baseline. We provide new local-optimization methods for estimating the multiclass DCP under two different regimes, one in which the conditional confusion matrices for each protected sub-population are known, and one in which these cannot be estimated, for instance, because the classifier is inaccessible or because good-quality individual-level data is not available. These methods can be used to detect classifiers that likely treat a significant fraction of the population unfairly. Experiments demonstrate the accuracy of the methods. The code for the experiments is provided as supplementary material.
APA
Sabato, S., Treister, E. & Yom-Tov, E.. (2025). Disparate Conditional Prediction in Multiclass Classifiers. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:52508-52525 Available from https://proceedings.mlr.press/v267/sabato25a.html.

Related Material