Federated Learning based on Pruning and Recovery

arXiv:2403.15439v1 Announce Type: new
Abstract: A novel federated learning training framework for heterogeneous environments is presented, taking into account the diverse network speeds of clients in realistic settings. This framework integrates asynchronous learning algorithms and pruning techniques, effectively addressing the inefficiencies of traditional federated learning algorithms in scenarios involving heterogeneous devices, as well as tackling the staleness issue and inadequate training of certain clients in asynchronous algorithms. Through the incremental restoration of model size during training, the framework expedites model …

abstract algorithms arxiv asynchronous cs.lg devices diverse environments federated learning framework network novel pruning recovery training type