Fairness in Federated Learning: Trends, Challenges, and Opportunities
Advanced Intelligent Systems · 2025-06 · 7 (6)
DOI: 10.1002/aisy.202400836 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Intelligent Systems, online erschienen am 06.04.2025. Verfasst von Noorain Mukhtiar und 2 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Research Council.
Abstract (Originalsprache)
At the intersection of the cutting‐edge technologies and privacy concerns, federated learning (FL) with its distributed architecture, stands at the forefront in a bid to facilitate collaborative model training across multiple clients while preserving data privacy. However, the applicability of FL systems is hindered by fairness concerns arising from numerous sources of heterogeneity that can result in biases and undermine a system's effectiveness, with skewed predictions, reduced accuracy, and inefficient model convergence. This survey thus explores the diverse sources of bias, including but not limited to, data, client, and model biases, and thoroughly discusses the strengths and limitations inherited within the array of the state‐of‐the‐art techniques utilized in the literature to mitigate such disparities in the FL training process. A comprehensive overview of the several notions, theoretical underpinnings, and technical aspects associated with fairness and their adoption in FL‐based multidisciplinary environments are delineated. Furthermore, the salient evaluation metrics leveraged to measure fairness quantitatively are examined. Finally, exciting open research directions that have the potential to drive future advancements in achieving fairer FL frameworks, in turn, offering a strong foundation for future research in this pivotal area are envisaged.
Förderung
- Australian Research Council
Zitieren
APA
Mukhtiar, N., Mahmood, A., & Sheng, Q. Z. (2025). Fairness in Federated Learning: Trends, Challenges, and Opportunities. Advanced Intelligent Systems, 7(6). https://doi.org/10.1002/aisy.202400836
Vancouver
Mukhtiar N, Mahmood A, Sheng QZ. Fairness in Federated Learning: Trends, Challenges, and Opportunities. Advanced Intelligent Systems. 2025;7(6). doi:10.1002/aisy.202400836
BibTeX
@article{Mukhtiar2025,
author = {Mukhtiar, Noorain and Mahmood, Adnan and Sheng, Quan Z.},
title = {Fairness in Federated Learning: Trends, Challenges, and Opportunities},
journal = {Advanced Intelligent Systems},
year = {2025},
volume = {7},
number = {6},
doi = {10.1002/aisy.202400836}
}
EUVIMED