Measuring Participant Contributions in Decentralized Federated Learning

2025-05-29

AI Summary

Addressing the critical lack of trustworthy and adaptive participant contribution quantification mechanisms in decentralized federated learning (DFL), this paper proposes the first DFL-specific contribution evaluation framework. Grounded in Shapley value theory, we introduce DFL-Shapley—the first contribution metric explicitly designed for DFL—and develop DFL-MR, an efficient, scalable approximation algorithm. DFL-Shapley jointly models round-level local contribution accumulation and dynamic model exchange topologies, enabling distributed contribution estimation under asynchronous and time-varying network conditions. Experiments demonstrate that DFL-Shapley establishes an effective ground-truth benchmark; DFL-MR achieves high fidelity across diverse DFL settings (mean absolute error < 4.2%) and significantly outperforms existing methods adapted from centralized federated learning.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Multiagent Systems: Adversarial Agents
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Federated learning (FL) enables multiple clients to collaboratively train models without sharing their data. Measuring participant contributions in FL is crucial for incentivizing clients and ensuring transparency. While various methods have been proposed for contribution measurement, they are designed exclusively for centralized federated learning (CFL), where a central server collects and aggregates client models, along with evaluating their contributions. Meanwhile, decentralized federated learning (DFL), in which clients exchange models directly without a central server, has gained significant attention for mitigating communication bottlenecks and eliminating a single point of failure. However, applying existing contribution measurement methods to DFL is challenging due to the presence of multiple global models and the absence of a central server. In this study, we present novel methodologies for measuring participant contributions in DFL. We first propose DFL-Shapley, an extension of the Shapley value tailored for DFL, adapting this widely used CFL metric to decentralized settings. Given the impracticality of computing the ideal DFL-Shapley in real-world systems, we introduce DFL-MR, a computable approximation that estimates overall contributions by accumulating round-wise Shapley values. We evaluate DFL-Shapley and DFL-MR across various FL scenarios and compare them with existing CFL metrics. The experimental results confirm DFL-Shapley as a valid ground-truth metric and demonstrate DFL-MR's proximity to DFL-Shapley across various settings, highlighting their effectiveness as contribution metrics in DFL.

Problem

• Measuring participant contributions in decentralized federated learning
• Extending Shapley value for decentralized settings (DFL-Shapley)
• Proposing computable approximation DFL-MR for real-world systems

Innovation

• Extends Shapley value for decentralized FL
• Introduces DFL-MR for practical contribution estimation
• Validates metrics across diverse FL scenarios