Pré-Publication, Document De Travail Année : 2025

Set to Be Fair: Demographic Parity Constraints for Set-Valued Classification

Résumé

Set-valued classification is used in multiclass settings where confusion between classes can occur and lead to misleading predictions. However, its application may amplify discriminatory bias motivating the development of set-valued approaches under fairness constraints. In this paper, we address the problem of set-valued classification under demographic parity and expected size constraints. We propose two complementary strategies: an oracle-based method that minimizes classification risk while satisfying both constraints, and a computationally efficient proxy that prioritizes constraint satisfaction. For both strategies, we derive closed-form expressions for the (optimal) fair set-valued classifiers and use these to build plug-in, data-driven procedures for empirical predictions. We establish distribution-free convergence rates for violations of the size and fairness constraints for both methods, and under mild assumptions we also provide excess-risk bounds for the oracle-based approach. Empirical results demonstrate the effectiveness of both strategies and highlight the efficiency of our proxy method.

Fichier principal
Vignette du fichier
main.pdf (1.21 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05296075 , version 1 (04-10-2025)

Licence

Identifiants

  • HAL Id : hal-05296075 , version 1

Citer

Eyal Cohen, Christophe Denis, Mohamed Hebiri. Set to Be Fair: Demographic Parity Constraints for Set-Valued Classification. 2025. ⟨hal-05296075⟩
224 Consultations
161 Téléchargements

Partager

  • More