Skip to main content

Minimax pareto fairness: A multi objective perspective

Publication ,  Conference
Martinez, N; Bertran, M; Sapiro, G
Published in: 37th International Conference on Machine Learning, ICML 2020
January 1, 2020

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.

Duke Scholars

Published In

37th International Conference on Machine Learning, ICML 2020

Publication Date

January 1, 2020

Volume

PartF168147-9

Start / End Page

6711 / 6720
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Martinez, N., Bertran, M., & Sapiro, G. (2020). Minimax pareto fairness: A multi objective perspective. In 37th International Conference on Machine Learning, ICML 2020 (Vol. PartF168147-9, pp. 6711–6720).
Martinez, N., M. Bertran, and G. Sapiro. “Minimax pareto fairness: A multi objective perspective.” In 37th International Conference on Machine Learning, ICML 2020, PartF168147-9:6711–20, 2020.
Martinez N, Bertran M, Sapiro G. Minimax pareto fairness: A multi objective perspective. In: 37th International Conference on Machine Learning, ICML 2020. 2020. p. 6711–20.
Martinez, N., et al. “Minimax pareto fairness: A multi objective perspective.” 37th International Conference on Machine Learning, ICML 2020, vol. PartF168147-9, 2020, pp. 6711–20.
Martinez N, Bertran M, Sapiro G. Minimax pareto fairness: A multi objective perspective. 37th International Conference on Machine Learning, ICML 2020. 2020. p. 6711–6720.

Published In

37th International Conference on Machine Learning, ICML 2020

Publication Date

January 1, 2020

Volume

PartF168147-9

Start / End Page

6711 / 6720