ENGLISH
La vitrine de diffusion des publications et contributions des chercheurs de l'ÉTS
RECHERCHER

Taming the triangle: On the interplays between fairness, interpretability, and privacy in machine learning

Ferry, Julien, Aivodji, Ulrich, Gambs, Sébastien, Huguet, Marie-José et Siala, Mohamed. 2025. « Taming the triangle: On the interplays between fairness, interpretability, and privacy in machine learning ». Computational Intelligence, vol. 41, nº 4.

[thumbnail of Aivodji-U-2025-31482.pdf]
Prévisualisation
PDF
Aivodji-U-2025-31482.pdf - Version publiée
Licence d'utilisation : Creative Commons CC BY-NC.

Télécharger (1MB) | Prévisualisation

Résumé

Machine learning techniques are increasingly used for high-stakes decision-making, such as college admissions, loan attribution, or recidivism prediction. Thus, it is crucial to ensure that the models learnt can be audited or understood by human users, do not create or reproduce discrimination or bias and do not leak sensitive information regarding their training data. Indeed, interpretability, fairness, and privacy are key requirements for the development of responsible machine learning, and all three have been studied extensively during the last decade. However, they were mainly considered in isolation, while in practice they interplay with each other, either positively or negatively. In this survey paper, we review the literature on the interactions between these three desiderata. More precisely, for each pairwise interaction, we summarize the identified synergies and tensions. These findings highlight several fundamental theoretical and empirical conflicts, while also demonstrating that jointly considering these different requirements is challenging when one aims at preserving a high level of utility. To solve this issue, we also discuss possible conciliation mechanisms, showing that a careful design can enable to successfully handle these different concerns in practice.

Type de document: Article publié dans une revue, révisé par les pairs
Professeur:
Professeur
Aïvodji, Ulrich
Affiliation: Génie logiciel et des technologies de l'information
Date de dépôt: 21 août 2025 14:23
Dernière modification: 24 sept. 2025 22:44
URI: https://espace2.etsmtl.ca/id/eprint/31482

Actions (Authentification requise)

Dernière vérification avant le dépôt Dernière vérification avant le dépôt