Resource-Efficient and Delay-Aware Federated Learning Design under Edge Heterogeneity. (arXiv:2112.13926v2 [cs.NI] UPDATED)

Federated learning (FL) has emerged as a popular methodology for distributing
machine learning across wireless edge devices. In this work, we consider
optimizing the tradeoff between model performance and resource utilization in
FL, under device-server communication delays and device computation
heterogeneity. Our proposed StoFedDelAv algorithm incorporates a local-global
model combiner into the FL synchronization step. We theoretically characterize
the convergence behavior of StoFedDelAv and obtain the optimal combiner
weights, which consider the global model delay and expected local gradient
error …

arxiv design edge federated learning learning