Multiplayer Federated Learning: Reaching Equilibrium with Less Communication

TL;DR

This paper introduces Multiplayer Federated Learning (MpFL), modeling clients as strategic players aiming for equilibrium, and proposes PEARL-SGD to achieve this with reduced communication, supported by theoretical analysis and experiments.

Contribution

It presents a game-theoretic framework for federated learning and introduces PEARL-SGD, a novel algorithm that reaches equilibrium efficiently with less communication.

Findings

PEARL-SGD converges to a neighborhood of equilibrium.

Theoretical analysis shows reduced communication needs.

Numerical experiments validate the theoretical results.

Abstract

Traditional Federated Learning (FL) approaches assume collaborative clients with aligned objectives working towards a shared global model. However, in many real-world scenarios, clients act as rational players with individual objectives and strategic behaviors, a concept that existing FL frameworks are not equipped to adequately address. To bridge this gap, we introduce Multiplayer Federated Learning (MpFL), a novel framework that models the clients in the FL environment as players in a game-theoretic context, aiming to reach an equilibrium. In this scenario, each player tries to optimize their own utility function, which may not align with the collective goal. Within MpFL, we propose Per-Player Local Stochastic Gradient Descent (PEARL-SGD), an algorithm in which each player/client performs local updates independently and periodically communicates with other players. We theoretically analyze PEARL-SGD and prove that it reaches a neighborhood of equilibrium with less communication in the stochastic setup compared to its non-local counterpart. Finally, we verify our theoretical findings through numerical experiments.