Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspective

TL;DR

This paper introduces a game-theoretical framework for incentivizing participant collaboration in federated learning, focusing on participant-centric models and addressing issues like free-riding.

Contribution

It proposes two novel game models for participant-centric federated learning, analyzing their equilibria and designing algorithms to promote effective collaboration.

Findings

CAFL reduces free-riding compared to COFL

Optimal thresholds improve collaboration efficiency

Game-theoretic analysis ensures stable equilibria

Abstract

Federated learning (FL) is a promising distributed framework for collaborative artificial intelligence model training while protecting user privacy. A bootstrapping component that has attracted significant research attention is the design of incentive mechanism to stimulate user collaboration in FL. The majority of works adopt a broker-centric approach to help the central operator to attract participants and further obtain a well-trained model. Few works consider forging participant-centric collaboration among participants to pursue an FL model for their common interests, which induces dramatic differences in incentive mechanism design from the broker-centric FL. To coordinate the selfish and heterogeneous participants, we propose a novel analytic framework for incentivizing effective and efficient collaborations for participant-centric FL. Specifically, we respectively propose two novel game models for contribution-oblivious FL (COFL) and contribution-aware FL (CAFL), where the latter one implements a minimum contribution threshold mechanism. We further analyze the uniqueness and existence for Nash equilibrium of both COFL and CAFL games and design efficient algorithms to achieve equilibrium solutions. Extensive performance evaluations show that there exists free-riding phenomenon in COFL, which can be greatly alleviated through the adoption of CAFL model with the optimized minimum threshold.