FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
This addresses communication bottlenecks in privacy-preserving collaborative training for distributed systems, but it is incremental as it builds on existing FL methods.
FedDM tackles the problem of communication inefficiency in federated learning due to unbalanced and non-i.i.d. data by using synthetic data to match loss landscapes, reducing communication rounds and improving model performance on image classification datasets.
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 the loss landscape. In detail, we construct synthetic sets of data on each client to locally match the loss landscape from original data through distribution matching. FedDM reduces communication rounds and improves model quality by transmitting more informative and smaller synthesized data compared with unwieldy model weights. We conduct extensive experiments on three image classification datasets, and results show that our method can outperform other FL counterparts in terms of efficiency and model performance. Moreover, we demonstrate that FedDM can be adapted to preserve differential privacy with Gaussian mechanism and train a better model under the same privacy budget.