Fairness Aware Counterfactuals for Subgroups - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Fairness Aware Counterfactuals for Subgroups

Abstract

In this work, we present Fairness Aware Counterfactuals for Subgroups (FACTS), a framework for auditing subgroup fairness through counterfactual explanations. We start with revisiting (and generalizing) existing notions and introducing new, more refined notions of subgroup fairness. We aim to (a) formulate different aspects of the difficulty of individuals in certain subgroups to achieve recourse, i.e. receive the desired outcome, either at the micro level, considering members of the subgroup individually, or at the macro level, considering the subgroup as a whole, and (b) introduce notions of subgroup fairness that are robust, if not totally oblivious, to the cost of achieving recourse. We accompany these notions with an efficient, model-agnostic, highly parameterizable, and explainable framework for evaluating subgroup fairness. We demonstrate the advantages, the wide applicability, and the efficiency of our approach through a thorough experimental evaluation of different benchmark datasets.
Fichier principal
Vignette du fichier
2306.14978.pdf (592.28 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04294292 , version 1 (19-11-2023)

Identifiers

Cite

Loukas Kavouras, Konstantinos Tsopelas, Giorgos Giannopoulos, Dimitris Sacharidis, Eleni Psaroudaki, et al.. Fairness Aware Counterfactuals for Subgroups. NeurIPS 2023 - 37th Conference on Neural Information Processing Systems, Dec 2023, New-Orleans, Lousiane, United States. ⟨hal-04294292⟩
55 View
18 Download

Altmetric

Share

Gmail Facebook X LinkedIn More