EUVIMEDEUVIMED entdecken
Crossref

Greedy Shapley Client Selection for Communication-Efficient Federated Learning

Pranava Singhal, Shashi Raj Pandey, Petar Popovski

IEEE Networking Letters · 2024-06 · 6 (2) · 134-138

DOI: 10.1109/lnet.2024.3363620 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Networking Letters, 2024-06. Verfasst von Pranava Singhal und 2 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 20 Literaturangaben. Gefördert von: Villum Investigator Grant “WATER” from the Velux Foundation, Denmark, European Union’s Horizon Project 6G-XCEL.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The standard client selection algorithms for Federated Learning (FL) are often unbiased and involve uniform random sampling of clients. This has been proven sub-optimal for fast convergence under practical settings characterized by significant heterogeneity in data distribution, computing, and communication resources across clients. For applications having timing constraints due to limited communication opportunities with the parameter server (PS), the client selection strategy is critical to complete model training within the fixed budget of communication rounds. To address this, we develop a biased client selection strategy, GreedyFed, that identifies and greedily selects the most contributing clients in each communication round. This method builds on a fast approximation algorithm for the Shapley Value at the PS, making the computation tractable for real-world applications with many clients. Compared to various client selection strategies on several real-world datasets, GreedyFed demonstrates fast and stable convergence with high accuracy under timing constraints and when imposing a higher degree of heterogeneity in data distribution, systems constraints, and privacy requirements.

Förderung

  • Villum Investigator Grant “WATER” from the Velux Foundation, Denmark
  • European Union’s Horizon Project 6G-XCEL

Zitieren

APA

Singhal, P., Pandey, S. R., & Popovski, P. (2024). Greedy Shapley Client Selection for Communication-Efficient Federated Learning. IEEE Networking Letters, 6(2), 134-138. https://doi.org/10.1109/lnet.2024.3363620

Vancouver

Singhal P, Pandey SR, Popovski P. Greedy Shapley Client Selection for Communication-Efficient Federated Learning. IEEE Networking Letters. 2024;6(2):134-138. doi:10.1109/lnet.2024.3363620

BibTeX
@article{Singhal2024,
  author = {Singhal, Pranava and Pandey, Shashi Raj and Popovski, Petar},
  title = {Greedy Shapley Client Selection for Communication-Efficient Federated Learning},
  journal = {IEEE Networking Letters},
  year = {2024},
  volume = {6},
  number = {2},
  pages = {134--138},
  doi = {10.1109/lnet.2024.3363620}
}
Kostenlos starten →