Survey on Fairness Notions and Related Tensions - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Survey on Fairness Notions and Related Tensions

Guilherme Alves
Fabien Bernier
  • Fonction : Auteur
  • PersonId : 1083723
Miguel Couceiro
Karima Makhlouf
  • Fonction : Auteur
  • PersonId : 1120695
Sami Zhioua
  • Fonction : Auteur
  • PersonId : 1120696

Résumé

Automated decision systems are increasingly used to take consequential decisions in problems such as job hiring and loan granting with the hope of replacing subjective human decisions with objective machine learning (ML) algorithms. ML-based decision systems, however, are found to be prone to bias which result in yet unfair decisions. Several notions of fairness have been defined in the literature to capture the different subtleties of this ethical and social concept (e.g. statistical parity, equal opportunity, etc.). Fairness requirements to be satisfied while learning models created several types of tensions among the different notions of fairness, but also with other desirable properties such as privacy and classification accuracy. \rev{This paper surveys the commonly used fairness notions and discusses the tensions that exist among them and with privacy and accuracy. Different methods to address the fairness-accuracy trade-off (classified into four approaches, namely, pre-processing, in-processing, post-processing, and hybrid) are reviewed. The survey is consolidated with experimental analysis carried out on fairness benchmark datasets to illustrate the relationship between fairness measures and accuracy on real-world scenarios.
Fichier principal
Vignette du fichier
_DAMI__Survey_on_Fairness_Notions_and_Related_Tensions (5).pdf (465.49 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03484009 , version 1 (16-12-2021)
hal-03484009 , version 2 (10-06-2022)
hal-03484009 , version 3 (19-06-2023)

Identifiants

  • HAL Id : hal-03484009 , version 2

Citer

Guilherme Alves, Fabien Bernier, Miguel Couceiro, Karima Makhlouf, Catuscia Palamidessi, et al.. Survey on Fairness Notions and Related Tensions. 2022. ⟨hal-03484009v2⟩
326 Consultations
282 Téléchargements

Partager

Gmail Facebook X LinkedIn More