Fair Without Leveling Down: A New Intersectional Fairness Definition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Fair Without Leveling Down: A New Intersectional Fairness Definition

Résumé

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.
Fichier principal
Vignette du fichier
IntersectionalFairnessMetric.pdf (534.77 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04273353 , version 1 (07-11-2023)

Licence

Paternité

Identifiants

Citer

Gaurav Maheshwari, Aurélien Bellet, Pascal Denis, Mikaela Keller. Fair Without Leveling Down: A New Intersectional Fairness Definition. EMNLP 2023 - The 2023 Conference on Empirical Methods in Natural Language Processing, Empirical Methods in Natural Language Processing, Dec 2023, Singapore (SG), Singapore. ⟨hal-04273353⟩
70 Consultations
84 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More