S-VOTE: Similarity-based Voting for Client Selection in Decentralized Federated Learning
This addresses resource efficiency and model performance challenges for decentralized federated learning systems, particularly in heterogeneous environments, though it appears incremental as it builds on existing client selection methods.
The paper tackles the problem of suboptimal models and high resource usage in decentralized federated learning with non-IID data by proposing S-VOTE, a voting-based client selection mechanism. The results show up to 21% lower communication costs, 4-6% faster convergence, 9-17% improved local performance, and 14-24% energy reduction compared to baselines.
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.