EUVIMEDEUVIMED entdecken
Crossref

How Valuable is Your Data? Optimizing Client Recruitment in Federated Learning

Yichen Ruan, Xiaoxi Zhang, Carlee Joe-Wong

IEEE/ACM Transactions on Networking · 2024-10 · 32 (5) · 4207-4221

DOI: 10.1109/tnet.2024.3422264 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE/ACM Transactions on Networking, 2024-10. Verfasst von Yichen Ruan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Young Outstanding Award under Zhujiang Talent Plan of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning allows distributed clients to train a shared machine learning model while preserving user privacy. In this framework, user devices (i.e., clients) perform local iterations of the learning algorithm on their data. These updates are periodically aggregated to form a shared model. Thus, a client represents the bundle of the user data, the device, and the user’s willingness to participate: since participating in federated learning requires clients to expend resources and reveal some information about their data, users may require some form of compensation to contribute to the training process. Recruiting more users generally results in higher accuracy, but slower completion time and higher cost. We propose the first work to theoretically analyze the resulting performance tradeoffs in deciding which clients to recruit for the federated learning algorithm. Our framework accounts for both accuracy (training and testing) and efficiency (completion time and cost) metrics. We provide solutions to this NP-Hard optimization problem and verify the value of client recruitment in experiments on synthetic and real-world data. The results of this work can serve as a guideline for the real-world deployment of federated learning and an initial investigation of the client recruitment problem.

Förderung

  • National Natural Science Foundation of China
  • Guangdong Basic and Applied Basic Research Foundation
  • Young Outstanding Award under Zhujiang Talent Plan of Guangdong Province
  • National Science Foundation

Zitieren

APA

Ruan, Y., Zhang, X., & Joe-Wong, C. (2024). How Valuable is Your Data? Optimizing Client Recruitment in Federated Learning. IEEE/ACM Transactions on Networking, 32(5), 4207-4221. https://doi.org/10.1109/tnet.2024.3422264

Vancouver

Ruan Y, Zhang X, Joe-Wong C. How Valuable is Your Data? Optimizing Client Recruitment in Federated Learning. IEEE/ACM Transactions on Networking. 2024;32(5):4207-4221. doi:10.1109/tnet.2024.3422264

BibTeX
@article{Ruan2024,
  author = {Ruan, Yichen and Zhang, Xiaoxi and Joe-Wong, Carlee},
  title = {How Valuable is Your Data? Optimizing Client Recruitment in Federated Learning},
  journal = {IEEE/ACM Transactions on Networking},
  year = {2024},
  volume = {32},
  number = {5},
  pages = {4207--4221},
  doi = {10.1109/tnet.2024.3422264}
}
Kostenlos starten →