Subjective Fairness: Fairness is in the eye of the beholder

Abstract : We introduce a natural, and widely applicable framework for fairness that relies on the available information. We develop algorithms for achieving a few different notions of fairness within a subjective framework, and in particular recently proposed concepts of fairness that are grounded in concepts of similarity and conditional independence. We argue that a suitable notion of similarity in the Bayesian setting is distributional similarity conditioned on the observations. For the latter, as independence is difficult to achieve uniformly in the Bayesian setting, we suggest a relaxation, for which we provide a small experimental demonstration.
Type de document :
Pré-publication, Document de travail
2017
Liste complète des métadonnées

https://hal.inria.fr/hal-01531849
Contributeur : Christos Dimitrakakis <>
Soumis le : lundi 10 juillet 2017 - 19:58:19
Dernière modification le : mercredi 15 août 2018 - 15:52:01
Document(s) archivé(s) le : mercredi 24 janvier 2018 - 18:38:25

Fichier

1706.00119.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01531849, version 2
  • ARXIV : 1706.00119

Citation

Christos Dimitrakakis, Yang Liu, David Parkes, Goran Radanovic. Subjective Fairness: Fairness is in the eye of the beholder. 2017. 〈hal-01531849v2〉

Partager

Métriques

Consultations de la notice

300

Téléchargements de fichiers

104