Bias in Federated Learning: A Comprehensive Survey
ACM Computing Surveys · 30.11.2025 · 57 (11) · 1-36
DOI: 10.1145/3735125 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 15.06.2025. Verfasst von Nawel Benarba und 1 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 168 Literaturangaben. Gefördert von: Agence Nationale de la Recherche.
Abstract (Originalsprache)
Federated Learning (FL) enables collaborative model training over multiple clients’ data, without sharing these data for better privacy. Addressing bias in FL remains a challenge. In this article, we first present a taxonomy of FL bias, presenting the causes and the different types of FL bias, namely demographic bias, performance-related bias, and contribution-related bias. We then categorize FL bias mitigation, in terms of used methods and provided guarantees, before providing a comprehensive and comparative analysis of existing works. Finally, we highlight key challenges and open research directions, including the impact of FL bias mitigation on model utility, privacy, and robustness.
Förderung
- Agence Nationale de la Recherche
Zitieren
APA
Benarba, N., & Bouchenak, S. (2025). Bias in Federated Learning: A Comprehensive Survey. ACM Computing Surveys, 57(11), 1-36. https://doi.org/10.1145/3735125
Vancouver
Benarba N, Bouchenak S. Bias in Federated Learning: A Comprehensive Survey. ACM Computing Surveys. 2025;57(11):1-36. doi:10.1145/3735125
BibTeX
@article{Benarba2025,
author = {Benarba, Nawel and Bouchenak, Sara},
title = {Bias in Federated Learning: A Comprehensive Survey},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {11},
pages = {1--36},
doi = {10.1145/3735125}
}
EUVIMED