Free-rider Attacks on Model Aggregation in Federated Learning - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2021

Free-rider Attacks on Model Aggregation in Federated Learning

Abstract

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.
Fichier principal
Vignette du fichier
free_riding_AISTATS_vf.pdf (1.5 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03123638 , version 1 (12-02-2021)

Identifiers

  • HAL Id : hal-03123638 , version 1

Cite

Yann Fraboni, Richard Vidal, Marco Lorenzi. Free-rider Attacks on Model Aggregation in Federated Learning. AISTATS 2021 - 24th International Conference on Artificial Intelligence and Statistics, Apr 2021, San Diego, United States. ⟨hal-03123638⟩
200 View
150 Download

Share

More