Fair Without Leveling Down: A New Intersectional Fairness Definition
Abstract
In this work, we consider the problem of intersectional group fairness in the classification setting, where the objective is to learn discrimination-free models in the presence of several intersecting sensitive groups. First, we illustrate various shortcomings of existing fairness measures commonly used to capture intersectional fairness. Then, we propose a new definition called the -Intersectional Fairness, which combines the absolute and the relative performance across sensitive groups and can be seen as a generalization of the notion of differential fairness. We highlight several desirable properties of the proposed definition and analyze its relation to other fairness measures. Finally, we benchmark multiple popular in-processing fair machine learning approaches using our new fairness definition and show that they do not achieve any improvement over a simple baseline. Our results reveal that the increase in fairness measured by previous definitions hides a "leveling down" effect, i.e., degrading the best performance over groups rather than improving the worst one.
Cite
@article{arxiv.2305.12495,
title = {Fair Without Leveling Down: A New Intersectional Fairness Definition},
author = {Gaurav Maheshwari and Aurélien Bellet and Pascal Denis and Mikaela Keller},
journal= {arXiv preprint arXiv:2305.12495},
year = {2023}
}
Comments
The paper has been accepted at: The 2023 Conference on Empirical Methods in Natural Language Processing