Incentivizing High-quality Participation From Federated Learning Agents

TL;DR

This paper introduces an incentive-aware framework for federated learning that encourages high-quality participation from self-interested agents by considering data heterogeneity and employing game-theoretic mechanisms to improve convergence.

Contribution

It proposes a novel incentive mechanism using Wasserstein distance and peer prediction to motivate truthful, high-quality contributions in federated learning with heterogeneous data.

Findings

The framework accelerates convergence in federated learning.

The peer prediction mechanism ensures truthful reporting from agents.

Experiments validate the effectiveness of the proposed incentives.

Abstract

Federated learning (FL) provides a promising paradigm for facilitating collaboration between multiple clients that jointly learn a global model without directly sharing their local data. However, existing research suffers from two caveats: 1) From the perspective of agents, voluntary and unselfish participation is often assumed. But self-interested agents may opt out of the system or provide low-quality contributions without proper incentives; 2) From the mechanism designer's perspective, the aggregated models can be unsatisfactory as the existing game-theoretical federated learning approach for data collection ignores the potential heterogeneous effort caused by contributed data. To alleviate above challenges, we propose an incentive-aware framework for agent participation that considers data heterogeneity to accelerate the convergence process. Specifically, we first introduce the notion of Wasserstein distance to explicitly illustrate the heterogeneous effort and reformulate the existing upper bound of convergence. To induce truthful reporting from agents, we analyze and measure the generalization error gap of any two agents by leveraging the peer prediction mechanism to develop score functions. We further present a two-stage Stackelberg game model that formalizes the process and examines the existence of equilibrium. Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed mechanism.