Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning

Yann Fraboni (1, 2) , Richard Vidal (2) , Laetitia Kameni (2) , Marco Lorenzi (1)

1 EPIONE - E-Patient : Images, données & mOdèles pour la médeciNe numériquE
2 Accenture Labs [Sophia Antipolis]

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 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.

Mots clés: Client sampling; federated learning; sampling variance; data representativity

Domaines: Informatique [cs]; Intelligence artificielle [cs.AI]

Yann Fraboni, Richard Vidal, Laetitia Kameni, Marco Lorenzi. Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning. ICML 2021 - 38th International Conference on Machine Learning, Jul 2021, online, United States. ⟨hal-03232421⟩