Local Coefficient Optimization in Federated Learning

Congliang Chen, Chi Zhang, Bingzhe Wu, Yatao Bian, Zhi-Quan Luo, Peilin ZhaoICLR 2023 · OpenReview

Abstract

Federated learning emerges as a promising approach to build a large-scale cooperative learning system among multiple clients without sharing their raw data. However, given a specific global objective, finding the optimal sampling weights for each client remains largely unexplored. This is particularly challenging when clients' data distributions are non-i.i.d. and clients partially participate. In this paper, we model the above task as a bi-level optimization problem which takes the correlations among different clients into account. We present a double-loop primal-dual-based algorithm to solve the bi-level optimization problem. We further provide rigorous convergence analysis for our algorithm under mild assumptions. Finally, we perform extensive empirical studies under both toy examples and learning models from real datasets to verify the effectiveness of the proposed method.
BibTeX
@inproceedings{chen2023local,
  author = {Congliang Chen and Chi Zhang and Bingzhe Wu and Yatao Bian and Zhi-Quan Luo and Peilin Zhao},
  title = {{Local Coefficient Optimization in Federated Learning}},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=xQXHkKI_7TG},
}

Loading related content...

Figure