Provably Personalized and Robust Federated Learning
This addresses the problem of efficient and secure personalization in federated learning for applications like healthcare or finance, though it appears incremental as it builds on existing clustering approaches with new guarantees.
The paper tackles the challenge of provably and optimally clustering clients in federated learning to train personalized models per cluster, achieving optimal convergence rates for a broad class of loss functions and robustness against malicious clients.
Identifying clients with similar objectives and learning a model-per-cluster is an intuitive and interpretable approach to personalization in federated learning. However, doing so with provable and optimal guarantees has remained an open challenge. We formalize this problem as a stochastic optimization problem, achieving optimal convergence rates for a large class of loss functions. We propose simple iterative algorithms which identify clusters of similar clients and train a personalized model-per-cluster, using local client gradients and flexible constraints on the clusters. The convergence rates of our algorithms asymptotically match those obtained if we knew the true underlying clustering of the clients and are provably robust in the Byzantine setting where some fraction of the clients are malicious.