Fair Without Leveling Down: A New Intersectional Fairness Definition

Gaurav Maheshwari, Aurélien Bellet, Pascal Denis, Mikaela Keller


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 𝛼-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.
Anthology ID:
2023.emnlp-main.558
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9018–9032
Language:
URL:
https://aclanthology.org/2023.emnlp-main.558
DOI:
10.18653/v1/2023.emnlp-main.558
Bibkey:
Cite (ACL):
Gaurav Maheshwari, Aurélien Bellet, Pascal Denis, and Mikaela Keller. 2023. Fair Without Leveling Down: A New Intersectional Fairness Definition. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9018–9032, Singapore. Association for Computational Linguistics.
Cite (Informal):
Fair Without Leveling Down: A New Intersectional Fairness Definition (Maheshwari et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.558.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.558.mp4