On the Applicability of ML Fairness Notions - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue SIGKDD Explorations Newsletter Année : 2021

On the Applicability of ML Fairness Notions

Résumé

Machine Learning (ML) based predictive systems are increasingly used to support decisions with a critical impact on individuals' lives such as college admission, job hiring, child custody, criminal risk assessment, etc. As a result, fairness emerged as an important requirement to guarantee that ML predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity of viewing the concept of fairness, several notions of fairness have been introduced in the literature. This paper is a survey of fairness notions that, unlike other surveys in the literature, addresses the question of "which notion of fairness is most suited to a given real-world scenario and why?". Our attempt to answer this question consists in (1) identifying the set of fairness-related characteristics of the real-world scenario at hand, (2) analyzing the behavior of each fairness notion, and then (3) fitting these two elements to recommend the most suitable fairness notion in every specific setup. The results are summarized in a decision diagram that can be used by practitioners and policy makers to navigate the relatively large catalogue of ML fairness notions.
Fichier non déposé

Dates et versions

hal-03091436 , version 1 (31-12-2020)

Identifiants

Citer

Karima Makhlouf, Sami Zhioua, Catuscia Palamidessi. On the Applicability of ML Fairness Notions. SIGKDD Explorations Newsletter, 2021, 23 (1), pp.14-23. ⟨10.1145/3468507.3468511⟩. ⟨hal-03091436⟩
112 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More