S-VOTE: Similarity-based Voting for Client Selection in Decentralized Federated Learning

2025-01-31

AI Summary

To address key challenges in decentralized federated learning (DFL)—including degraded model performance under non-IID data, high communication overhead, and uneven resource utilization—this paper proposes a similarity-driven, distributed voting-based client selection mechanism. Eschewing centralized coordination, the method dynamically assesses client contribution potential via cosine similarity, integrates distributed consensus, and employs adaptive local training scheduling to enable lightweight collaboration across heterogeneous devices. The core innovation lies in the first integration of similarity modeling with a voting mechanism, which adaptively activates underutilized clients while jointly optimizing load balancing and model convergence. Experimental results demonstrate significant improvements over mainstream baselines: up to 21% reduction in communication cost, 4–6% faster convergence, 9–17% higher local model accuracy, and 14–24% lower energy consumption.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Decentralized Federated Learning (DFL) enables collaborative, privacy-preserving model training without relying on a central server. This decentralized approach reduces bottlenecks and eliminates single points of failure, enhancing scalability and resilience. However, DFL also introduces challenges such as suboptimal models with non-IID data distributions, increased communication overhead, and resource usage. Thus, this work proposes S-VOTE, a voting-based client selection mechanism that optimizes resource usage and enhances model performance in federations with non-IID data conditions. S-VOTE considers an adaptive strategy for spontaneous local training that addresses participation imbalance, allowing underutilized clients to contribute without significantly increasing resource costs. Extensive experiments on benchmark datasets demonstrate the S-VOTE effectiveness. More in detail, it achieves lower communication costs by up to 21%, 4-6% faster convergence, and improves local performance by 9-17% compared to baseline methods in some configurations, all while achieving a 14-24% energy consumption reduction. These results highlight the potential of S-VOTE to address DFL challenges in heterogeneous environments.

Problem

• Decentralized Federated Learning
• Data Imbalance
• Communication Efficiency

Innovation

• Decentralized Federated Learning
• Efficient Resource Allocation
• Communication Cost Reduction