1. On the Applicability of ML Fairness Notions
- Author
-
Makhlouf, Karima, Zhioua, Sami, Palamidessi, Catuscia, Université du Québec à Montréal UQAM, Higher Colleges of Technology Dubai, UAE, Concurrency, Mobility and Transactions (COMETE), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'informatique de l'École polytechnique [Palaiseau] (LIX), Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X), ANR-16-CE25-0011,REPAS,Des systèmes logiciels fiables et conscients des données privées, via les métriques de bisimulation(2016), European Project: 835294,H2020 Pilier ERC,HYPATIA(2019), Laboratoire d'informatique de l'École polytechnique [Palaiseau] (LIX), École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
- Subjects
[INFO.INFO-CY]Computer Science [cs]/Computers and Society [cs.CY] ,[INFO]Computer Science [cs] ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] - Abstract
International audience; 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.
- Published
- 2020
- Full Text
- View/download PDF