To enhance straggler resilience in federated learning (FL) systems, a semi-decentralized approach has been recently proposed, enabling collaboration between clients. Unlike the existing semi-decentralized schemes, which adaptively adjust the collaboration weight according to the network topology, this letter proposes a deterministic coded network that leverages wireless diversity for semi-decentralized FL without requiring prior information about the entire network. Furthermore, the theoretical analyses of the outage and the convergence rate of the proposed scheme are provided. Finally, the superiority of our proposed method over benchmark methods is demonstrated through comprehensive simulations.
@article{arxiv.2406.19002,
title = {Supplementary File: Coded Cooperative Networks for Semi-Decentralized Federated Learning},
author = {Shudi Weng and Ming Xiao and Chao Ren and Mikael Skoglund},
journal= {arXiv preprint arXiv:2406.19002},
year = {2025}
}