Compressed Hierarchical Federated Learning for Edge-Level Imbalanced Wireless Networks
Yuan Liu, Zhe Qu, Jianxin Wang · IEEE Transactions on Computational Social Systems · 2025
Federated learning (FL) serves as a distributed framework facilitating privacy-preserving machine learning on vast data generated by mobile and IoT devices. Hierarchical federated averaging (H-FedAvg) has emerged as a solution to the communication bottleneck, enabling large-scale implementation. It leverages the client-edge-cloud aggregation hierarchy, capitalizing on the accessibility of the cloud server and the communication efficiency of edge servers (ESs). However, the full potential of H-FedAvg in real-world scenarios, particularly in the presence of imbalanced ES communication latency, remains largely unexplored. This article delves into the issue of imbalanced communication latency and introduces the edge-level imbalanced H-FedAvg (IH-FedAvg) algorithm, accompanied by convergence analysis. Theoretical and empirical results underscore the degradation of IH-FedAvg, which is influenced by the number of edge aggregation rounds and the divergence between the slowest and fastest ESs. To tackle this challenge, we propose an error-feedback compression method, leading to the edge-level compressed H-FedAvg (ECH-FedAvg) algorithm. Theoretical analysis indicates that the convergence performance depends on the compressor ratio. Going beyond compression, we present a joint optimization approach that considers both compressor ratio selection and bandwidth allocation, dynamically guiding ECH-FedAvg. Extensive experiments show that ECH-FedAvg achieves competitive performance compared to H-FedAvg, significantly enhancing communication efficiency. These findings underscore the potential of ECH-FedAvg in addressing challenges related to imbalanced communication in real-world networks.