Stochastic Client Selection for Federated Learning With Volatile Clients

Authors:
Top Cited Papers
Publisher website
Google Scholar
Abstract
Federated learning (FL), arising as a privacy-preserving machine learning paradigm, has received notable attention from the public. In each round of synchronous FL training, only a fraction of available clients are chosen to participate, and the selection decision might have a significant effect on the training efficiency, as well as the final model performance. In this article, we investigate the client selection problem under a volatile context, in which the local training of heterogeneous clients is likely to fail due to various kinds of reasons and in different levels of frequency. Intuitively, too much training failure might potentially reduce the training efficiency, while too much selection on clients with greater stability might introduce bias, thereby resulting in degradation of the training effectiveness. To tackle this tradeoff, we, in this article, formulate the client selection problem under joint consideration of effective participation and fairness. Furthermore, we propose E3CS, a stochastic client selection scheme as a solution. According to our experimental results over a public data set, the proposed selection scheme is able to achieve up to $2\times $ faster convergence to a fixed model accuracy while maintaining the same level of final model accuracy, compared with the state-of-the-art selection schemes.
Funding Information
  • Key-Area Research and Development Program of Guangdong Province (2021B0101420002)
  • National Natural Science Foundation of China (62072187, 61872084)
  • Guangzhou Municipal Science and Technology Program key projects (202007040002)
  • Guangzhou Development Zone Science and Technology (2020GH10)
  • Guangdong Marine Economic Development Special Fund Project (GDNRC[2022]17)
  • Science and Technology Innovation 2030—“Brain Science and Brain-Like Research” Major Project (2021ZD0201402, 2021ZD0201405)

This publication has 13 references indexed in Scilit: