Mitigating Unfairness in Differentially-Private Federated Learning
ACM Transactions on Modeling and Performance Evaluation of Computing Systems · 30.06.2025 · 10 (2) · 1-25
DOI: 10.1145/3725847 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Modeling and Performance Evaluation of Computing Systems, online erschienen am 30.05.2025. Verfasst von Bingqian Du und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hubei Provincial Natural Science Foundation of China, Hong Kong RGC.
Abstract (Originalsprache)
Federated learning is a new learning paradigm which utilizes crowdsourced data stored at dispersed user devices (aka clients) to learn a global model. Studies have shown that even though data are kept on local devices, an adversary is still able to infer client information during the training process or from the learned model. Differential privacy has recently been introduced to deep learning model training, to protect data privacy of clients. Nonetheless, it exacerbates unfairness with the learned model among participating clients due to its uniform clipping and noise addition, even when the training loss function explicitly considers unfairness. To validate the impact of the differential privacy mechanism in federated learning, we carefully approximate the correlation between fairness performance across clients and the fundamental operations within the differential privacy mechanism and quantify the influence of differential privacy mechanisms on model performance across various clients. Subsequently, leveraging our theoretical findings regarding the effect of the differential privacy mechanism, we formulate the unfairness mitigation problem and propose an algorithm based on the modified method of differential multipliers. Extensive evaluation shows that our method outperforms state-of-the-art differentially private federated learning algorithm by about 30% for non-i.i.d. data distribution in terms of the variance of model performance across clients.
Förderung
- National Natural Science Foundation of China
- Hubei Provincial Natural Science Foundation of China
- Hong Kong RGC
Zitieren
APA
Du, B., Xiang, L., & Wu, C. (2025). Mitigating Unfairness in Differentially-Private Federated Learning. ACM Transactions on Modeling and Performance Evaluation of Computing Systems, 10(2), 1-25. https://doi.org/10.1145/3725847
Vancouver
Du B, Xiang L, Wu C. Mitigating Unfairness in Differentially-Private Federated Learning. ACM Transactions on Modeling and Performance Evaluation of Computing Systems. 2025;10(2):1-25. doi:10.1145/3725847
BibTeX
@article{Du2025,
author = {Du, Bingqian and Xiang, Liyao and Wu, Chuan},
title = {Mitigating Unfairness in Differentially-Private Federated Learning},
journal = {ACM Transactions on Modeling and Performance Evaluation of Computing Systems},
year = {2025},
volume = {10},
number = {2},
pages = {1--25},
doi = {10.1145/3725847}
}
EUVIMED