FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning. (arXiv:2207.09653v1 [cs.LG])

Federated learning~(FL) has recently attracted increasing attention from
academia and industry, with the ultimate goal of achieving collaborative
training under privacy and communication constraints. Existing iterative model
averaging based FL algorithms require a large number of communication rounds to
obtain a well-performed model due to extremely unbalanced and non-i.i.d data
partitioning among different clients. Thus, we propose FedDM to build the
global training objective from multiple local surrogate functions, which
enables the server to gain a more global view of …

communication distribution federated learning lg