Multiplayer Federated Learning: Reaching Equilibrium with Less Communication
This addresses federated learning scenarios where clients have individual objectives, offering a solution for decentralized and competitive environments, though it is incremental by extending FL with game theory.
The paper tackles the problem of federated learning with strategic clients by introducing Multiplayer Federated Learning (MpFL), modeling clients as game-theoretic players to reach equilibrium, and shows that the proposed PEARL-SGD algorithm achieves this with less communication in experiments.
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.