Minimax Pareto Fairness: A Multi Objective Perspective

Natalia Martinez, Martin Bertran, Guillermo Sapiro
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:6755-6764, 2020.

Abstract

In this work we formulate and formally characterize group fairness as a multi-objective optimization problem, where each sensitive group risk is a separate objective. We propose a fairness criterion where a classifier achieves minimax risk and is Pareto-efficient w.r.t. all groups, avoiding unnecessary harm, and can lead to the best zero-gap model if policy dictates so. We provide a simple optimization algorithm compatible with deep neural networks to satisfy these constraints. Since our method does not require test-time access to sensitive attributes, it can be applied to reduce worst-case classification errors between outcomes in unbalanced classification problems. We test the proposed methodology on real case-studies of predicting income, ICU patient mortality, skin lesions classification, and assessing credit risk, demonstrating how our framework compares favorably to other approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-martinez20a, title = {Minimax Pareto Fairness: A Multi Objective Perspective}, author = {Martinez, Natalia and Bertran, Martin and Sapiro, Guillermo}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {6755--6764}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/martinez20a/martinez20a.pdf}, url = {https://proceedings.mlr.press/v119/martinez20a.html}, abstract = {In this work we formulate and formally characterize group fairness as a multi-objective optimization problem, where each sensitive group risk is a separate objective. We propose a fairness criterion where a classifier achieves minimax risk and is Pareto-efficient w.r.t. all groups, avoiding unnecessary harm, and can lead to the best zero-gap model if policy dictates so. We provide a simple optimization algorithm compatible with deep neural networks to satisfy these constraints. Since our method does not require test-time access to sensitive attributes, it can be applied to reduce worst-case classification errors between outcomes in unbalanced classification problems. We test the proposed methodology on real case-studies of predicting income, ICU patient mortality, skin lesions classification, and assessing credit risk, demonstrating how our framework compares favorably to other approaches.} }
Endnote
%0 Conference Paper %T Minimax Pareto Fairness: A Multi Objective Perspective %A Natalia Martinez %A Martin Bertran %A Guillermo Sapiro %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-martinez20a %I PMLR %P 6755--6764 %U https://proceedings.mlr.press/v119/martinez20a.html %V 119 %X In this work we formulate and formally characterize group fairness as a multi-objective optimization problem, where each sensitive group risk is a separate objective. We propose a fairness criterion where a classifier achieves minimax risk and is Pareto-efficient w.r.t. all groups, avoiding unnecessary harm, and can lead to the best zero-gap model if policy dictates so. We provide a simple optimization algorithm compatible with deep neural networks to satisfy these constraints. Since our method does not require test-time access to sensitive attributes, it can be applied to reduce worst-case classification errors between outcomes in unbalanced classification problems. We test the proposed methodology on real case-studies of predicting income, ICU patient mortality, skin lesions classification, and assessing credit risk, demonstrating how our framework compares favorably to other approaches.
APA
Martinez, N., Bertran, M. & Sapiro, G.. (2020). Minimax Pareto Fairness: A Multi Objective Perspective. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:6755-6764 Available from https://proceedings.mlr.press/v119/martinez20a.html.

Related Material