Incentivizing Truthful Collaboration in Heterogeneous Federated Learning

Dimitar Chakarov, Nikita Tsoy, Kristian Minchev, Nikola Konstantinov

Keywords: Federated Learning, Heterogeneity, Game Theory, Incentive Design

TL;DR: We incentivize clients in federated learning to report truthful updates despite data heterogeneity

Abstract: It is well-known that Federated Learning (FL) is vulnerable to manipulated updates from clients. In this work we study the impact of data heterogeneity on clients' incentives to manipulate their updates. We formulate a game in which clients may upscale their gradient updates in order to ``steer'' the server model to their advantage. We develop a payment rule that disincentivizes sending large gradient updates, and steers the clients towards truthfully reporting their gradients. We also derive explicit bounds on the clients' payments and the convergence rate of the global model, which allows us to study the trade-off between heterogeneity, payments and convergence.

Submission Number: 104