Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning
This addresses communication inefficiencies and instability in federated learning, which is incremental as it builds on existing FL methods without requiring client-side changes.
The paper tackles the problem of optimizing server-client communications and training stability in federated learning by introducing clustered sampling for client selection, demonstrating through experiments in non-iid and unbalanced scenarios that it leads to better training convergence and reduced variability compared to standard approaches.
This work addresses the problem of optimizing communications between server and clients in federated learning (FL). Current sampling approaches in FL are either biased, or non optimal in terms of server-clients communications and training stability. To overcome this issue, we introduce \textit{clustered sampling} for clients selection. We prove that clustered sampling leads to better clients representatitivity and to reduced variance of the clients stochastic aggregation weights in FL. Compatibly with our theory, we provide two different clustering approaches enabling clients aggregation based on 1) sample size, and 2) models similarity. Through a series of experiments in non-iid and unbalanced scenarios, we demonstrate that model aggregation through clustered sampling consistently leads to better training convergence and variability when compared to standard sampling approaches. Our approach does not require any additional operation on the clients side, and can be seamlessly integrated in standard FL implementations. Finally, clustered sampling is compatible with existing methods and technologies for privacy enhancement, and for communication reduction through model compression.