Enforcing Individual Fairness via Rényi Variational Inference - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Enforcing Individual Fairness via Rényi Variational Inference

Vincent Grari
  • Fonction : Auteur
  • PersonId : 1178630
  • IdRef : 26491144X
Oualid El Hajouji
  • Fonction : Auteur
Marcin Detyniecki

Résumé

As opposed to group fairness algorithms which enforce equality of distributions, individual fairness aims at treating similar people similarly. In this paper, we focus on individual fairness regarding sensitive attributes that should be removed from people comparisons. In that aim, we present a new method that leverages the Variational Autoencoder (VAE) algorithm and the Hirschfeld-Gebelein-Renyi (HGR) maximal correlation coefficient for enforcing individual fairness in predictions. We also propose new metrics to assess individual fairness. We demonstrate the effectiveness of our approach in enforcing individual fairness on several machine learning tasks prone to algorithmic bias.
Fichier non déposé

Dates et versions

hal-03923301 , version 1 (04-01-2023)

Identifiants

Citer

Vincent Grari, Oualid El Hajouji, Sylvain Lamprier, Marcin Detyniecki. Enforcing Individual Fairness via Rényi Variational Inference. 28th International Conference on Neural Information Processing - ICONIP 2021, Dec 2021, Bali, Indonesia. pp.608-616, ⟨10.1007/978-3-030-92307-5_71⟩. ⟨hal-03923301⟩
14 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More