Fairness-Aware Neural Rényi Minimization for Continuous Features - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Fairness-Aware Neural Rényi Minimization for Continuous Features

Sylvain Lamprier
Marcin Detyniecki

Résumé

The past few years have seen a dramatic rise of academic and societal interest in fair machine learning. While plenty of fair algorithms have been proposed recently to tackle this challenge for discrete variables, only a few ideas exist for continuous ones. The objective in this paper is to ensure some independence level between the outputs of regression models and any given continuous sensitive variables. For this purpose, we use the Hirschfeld-Gebelein-Rényi (HGR) maximal correlation coefficient as a fairness metric. We propose to minimize the HGR coefficient directly with an adversarial neural network architecture. The idea is to predict the output Y while minimizing the ability of an adversarial neural network to find the estimated transformations which are required to predict the HGR coefficient. We empirically assess and compare our approach and demonstrate significant improvements on previously presented work in the field.

Dates et versions

hal-03923324 , version 1 (04-01-2023)

Identifiants

Citer

Vincent Grari, Sylvain Lamprier, Marcin Detyniecki. Fairness-Aware Neural Rényi Minimization for Continuous Features. Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}, Jul 2020, Yokohama, Japan. pp.2262-2268, ⟨10.24963/ijcai.2020/313⟩. ⟨hal-03923324⟩
34 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More