Fairness seen as Global Sensitivity Analysis - IRT Saint Exupéry - Institut de Recherche Technologique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Fairness seen as Global Sensitivity Analysis

Résumé

Ensuring that a predictor is not biased against a sensible feature is the key of Fairness learning. Conversely, Global Sensitivity Analysis is used in numerous contexts to monitor the influence of any feature on an output variable. We reconcile these two domains by showing how Fairness can be seen as a special framework of Global Sensitivity Analysis and how various usual indicators are common between these two fields. We also present new Global Sensitivity Analysis indices, as well as rates of convergence, that are useful as fairness proxies.
Fichier principal
Vignette du fichier
Fairness_seen_as_GSA.pdf (347.6 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03160697 , version 1 (05-03-2021)
hal-03160697 , version 2 (20-09-2021)

Identifiants

Citer

Clément Bénesse, Fabrice Gamboa, Jean-Michel Loubes, Thibaut Boissin. Fairness seen as Global Sensitivity Analysis. 2021. ⟨hal-03160697v1⟩
111 Consultations
225 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More