FedSoft: Soft Clustered Federated Learning with Proximal Local Updating
This work addresses federated learning for clients with mixed data distributions, offering a method to improve model personalization and efficiency, though it appears incremental as it builds on existing clustered approaches.
The paper tackles the problem of clustered federated learning by relaxing the hard association assumption to allow local datasets to follow mixtures of multiple source distributions, proposing FedSoft to train personalized and cluster models with proximal updates that reduce client workload, and shows it effectively exploits distribution similarities for good performance.
Traditionally, clustered federated learning groups clients with the same data distribution into a cluster, so that every client is uniquely associated with one data distribution and helps train a model for this distribution. We relax this hard association assumption to soft clustered federated learning, which allows every local dataset to follow a mixture of multiple source distributions. We propose FedSoft, which trains both locally personalized models and high-quality cluster models in this setting. FedSoft limits client workload by using proximal updates to require the completion of only one optimization task from a subset of clients in every communication round. We show, analytically and empirically, that FedSoft effectively exploits similarities between the source distributions to learn personalized and cluster models that perform well.