In this paper, we propose Hierarchical Federated Learning with Momentum Acceleration (HierMo), a three-tier worker-edge-cloud federated learning algorithm that applies momentum for training acceleration. Momentum is calculated and aggregated in the three tiers. We provide convergence analysis for HierMo, showing a convergence rate of O(1/T). In the analysis, we develop a new approach to characterize model aggregation, momentum aggregation, and their interactions. Based on this result, {we prove that HierMo achieves a tighter convergence upper bound compared with HierFAVG without momentum}. We also propose HierOPT, which optimizes the aggregation periods (worker-edge and edge-cloud aggregation periods) to minimize the loss given a limited training time.
@article{arxiv.2210.14560,
title = {Hierarchical Federated Learning with Momentum Acceleration in Multi-Tier Networks},
author = {Zhengjie Yang and Sen Fu and Wei Bao and Dong Yuan and Albert Y. Zomaya},
journal= {arXiv preprint arXiv:2210.14560},
year = {2022}
}