Federated Learning as a Network Effects Game

TL;DR

This paper models clients' participation in federated learning as a network effects game, analyzing incentives, equilibrium dynamics, and proposing a cost-effective payment scheme to optimize client engagement.

Contribution

It introduces the first model of client incentives in federated learning as a network effects game, analyzing equilibrium and designing incentive schemes.

Findings

Dynamics converge to equilibrium naturally

Proposed payment scheme incentivizes desired participation

Clients' benefits depend on other participating clients

Abstract

Federated Learning (FL) aims to foster collaboration among a population of clients to improve the accuracy of machine learning without directly sharing local data. Although there has been rich literature on designing federated learning algorithms, most prior works implicitly assume that all clients are willing to participate in a FL scheme. In practice, clients may not benefit from joining in FL, especially in light of potential costs related to issues such as privacy and computation. In this work, we study the clients' incentives in federated learning to help the service provider design better solutions and ensure clients make better decisions. We are the first to model clients' behaviors in FL as a network effects game, where each client's benefit depends on other clients who also join the network. Using this setup we analyze the dynamics of clients' participation and characterize the equilibrium, where no client has incentives to alter their decision. Specifically, we show that dynamics in the population naturally converge to equilibrium without needing explicit interventions. Finally, we provide a cost-efficient payment scheme that incentivizes clients to reach a desired equilibrium when the initial network is empty.