EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Federated Learning Client Pruning for Noisy Labels

Mahdi Morafah, Hojin Chang, Chen Chen, Bill Lin

ACM Transactions on Modeling and Performance Evaluation of Computing Systems · 30.06.2025 · 10 (2) · 1-25

DOI: 10.1145/3706058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Modeling and Performance Evaluation of Computing Systems, online erschienen am 30.05.2025. Verfasst von Mahdi Morafah und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning (FL) enables collaborative model training across decentralized edge devices while preserving data privacy. However, existing FL methods often assume clean annotated datasets, which are impractical for resource-constrained edge devices. In reality, noisy labels are prevalent, posing significant challenges to FL performance. Prior approaches attempt label correction and robust training techniques but exhibit limited efficacy, particularly under high noise levels. This article introduces ClipFL ( F ederated L earning Cli ent P runing), a novel framework addressing noisy labels from a fresh perspective. ClipFL identifies and excludes noisy clients based on their performance on a clean validation dataset, tracked using a Noise Candidacy Score (NCS). The framework includes three phases: pre-client pruning to identify potential noisy clients and calculate their NCS, client pruning to exclude a percentage of clients with the highest NCS, and post-client pruning for fine-tuning the global model with standard FL on clean clients. Empirical evaluation demonstrates ClipFL’s efficacy across diverse datasets and noise levels, achieving accurate noisy client identification, superior performance, faster convergence, and reduced communication costs compared to state-of-the-art FL methods. Our code is available at https://github.com/MMorafah/ClipFL .

Zitieren

APA

Morafah, M., Chang, H., Chen, C., & Lin, B. (2025). Federated Learning Client Pruning for Noisy Labels. ACM Transactions on Modeling and Performance Evaluation of Computing Systems, 10(2), 1-25. https://doi.org/10.1145/3706058

Vancouver

Morafah M, Chang H, Chen C, Lin B. Federated Learning Client Pruning for Noisy Labels. ACM Transactions on Modeling and Performance Evaluation of Computing Systems. 2025;10(2):1-25. doi:10.1145/3706058

BibTeX
@article{Morafah2025,
  author = {Morafah, Mahdi and Chang, Hojin and Chen, Chen and Lin, Bill},
  title = {Federated Learning Client Pruning for Noisy Labels},
  journal = {ACM Transactions on Modeling and Performance Evaluation of Computing Systems},
  year = {2025},
  volume = {10},
  number = {2},
  pages = {1--25},
  doi = {10.1145/3706058}
}
Kostenlos starten →