Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraints

Yao Yao, Qihang Lin, Tianbao Yang
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:10324-10342, 2023.

Abstract

As machine learning being used increasingly in making high-stakes decisions, an arising challenge is to avoid unfair AI systems that lead to discriminatory decisions for protected population. A direct approach for obtaining a fair predictive model is to train the model through optimizing its prediction performance subject to fairness constraints. Among various fairness constraints, the ones based on the area under the ROC curve (AUC) are emerging recently because they are threshold-agnostic and effective for unbalanced data. In this work, we formulate the problem of training a fairness-aware predictive model as an AUC optimization problem subject to a class of AUC-based fairness constraints. This problem can be reformulated as a min-max optimization problem with min-max constraints, which we solve by stochastic first-order methods based on a new Bregman divergence designed for the special structure of the problem. We numerically demonstrate the effectiveness of our approach on real-world data under different fairness metrics.

Cite this Paper


BibTeX
@InProceedings{pmlr-v206-yao23b, title = {Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraints}, author = {Yao, Yao and Lin, Qihang and Yang, Tianbao}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {10324--10342}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/yao23b/yao23b.pdf}, url = {https://proceedings.mlr.press/v206/yao23b.html}, abstract = {As machine learning being used increasingly in making high-stakes decisions, an arising challenge is to avoid unfair AI systems that lead to discriminatory decisions for protected population. A direct approach for obtaining a fair predictive model is to train the model through optimizing its prediction performance subject to fairness constraints. Among various fairness constraints, the ones based on the area under the ROC curve (AUC) are emerging recently because they are threshold-agnostic and effective for unbalanced data. In this work, we formulate the problem of training a fairness-aware predictive model as an AUC optimization problem subject to a class of AUC-based fairness constraints. This problem can be reformulated as a min-max optimization problem with min-max constraints, which we solve by stochastic first-order methods based on a new Bregman divergence designed for the special structure of the problem. We numerically demonstrate the effectiveness of our approach on real-world data under different fairness metrics.} }
Endnote
%0 Conference Paper %T Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraints %A Yao Yao %A Qihang Lin %A Tianbao Yang %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-yao23b %I PMLR %P 10324--10342 %U https://proceedings.mlr.press/v206/yao23b.html %V 206 %X As machine learning being used increasingly in making high-stakes decisions, an arising challenge is to avoid unfair AI systems that lead to discriminatory decisions for protected population. A direct approach for obtaining a fair predictive model is to train the model through optimizing its prediction performance subject to fairness constraints. Among various fairness constraints, the ones based on the area under the ROC curve (AUC) are emerging recently because they are threshold-agnostic and effective for unbalanced data. In this work, we formulate the problem of training a fairness-aware predictive model as an AUC optimization problem subject to a class of AUC-based fairness constraints. This problem can be reformulated as a min-max optimization problem with min-max constraints, which we solve by stochastic first-order methods based on a new Bregman divergence designed for the special structure of the problem. We numerically demonstrate the effectiveness of our approach on real-world data under different fairness metrics.
APA
Yao, Y., Lin, Q. & Yang, T.. (2023). Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraints. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:10324-10342 Available from https://proceedings.mlr.press/v206/yao23b.html.

Related Material