Testing Group Fairness via Optimal Transport Projections

Testing Group Fairness via Optimal Transport Projections

Authors: Nian Si, Karthyek Murthy, Jose Blanchet, Viet Anh Nguyen

ICML 2021 - to appear

AbstractBibtex
We present a statistical testing framework to detect if a given machine learning classifier fails to satisfy a wide range of group fairness notions. The proposed test is a flexible, interpretable, and statistically rigorous tool for auditing whether exhibited biases are intrinsic to the algorithm or due to the randomness in the data. The statistical challenges, which may arise from multiple impact criteria that define group fairness and which are discontinuous on model parameters, are conveniently tackled by projecting the empirical measure onto the set of group-fair probability models using optimal transport. This statistic is efficiently computed using linear programming and its asymptotic distribution is explicitly obtained. The proposed framework can also be used to test for testing composite fairness hypotheses and fairness with multiple sensitive attributes. The optimal transport testing formulation improves interpretability by characterizing the minimal covariate perturbations that eliminate the bias observed in the audit.

@inproceedings{ref:si2021testing,
title = “Testing Group Fairness via Optimal Transport Projections”,
author = {Nian Si and Karthyek Murthy and Jose Blanchet and Viet Anh Nguyen},
booktitle= {Proceedings of the 38th International Conference on Machine Learning},
year = {2021}
}