Incentivized Communication for Federated Bandits

TL;DR

This paper introduces an incentivized communication protocol for federated bandits, addressing the challenge of self-interested clients by motivating data sharing through incentives, and demonstrates its effectiveness with theoretical guarantees and empirical validation.

Contribution

It is the first to formalize incentivized communication in federated bandits and proposes Inc-FedUCB, achieving near-optimal regret with provable incentive and communication costs.

Findings

Inc-FedUCB achieves near-optimal regret.

The protocol reduces incentive and communication costs.

Empirical results validate effectiveness across datasets.

Abstract

Most existing works on federated bandits take it for granted that all clients are altruistic about sharing their data with the server for the collective good whenever needed. Despite their compelling theoretical guarantee on performance and communication efficiency, this assumption is overly idealistic and oftentimes violated in practice, especially when the algorithm is operated over self-interested clients, who are reluctant to share data without explicit benefits. Negligence of such self-interested behaviors can significantly affect the learning efficiency and even the practical operability of federated bandit learning. In light of this, we aim to spark new insights into this under-explored research area by formally introducing an incentivized communication problem for federated bandits, where the server shall motivate clients to share data by providing incentives. Without loss of generality, we instantiate this bandit problem with the contextual linear setting and propose the first incentivized communication protocol, namely, Inc-FedUCB, that achieves near-optimal regret with provable communication and incentive cost guarantees. Extensive empirical experiments on both synthetic and real-world datasets further validate the effectiveness of the proposed method across various environments.