What question did this study set out to answer?

This work aims to improve client selection in decentralized federated learning while addressing challenges with non-IID data.

February 11, 2026Open Access

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

View Full Paper

Ask AI

Bookmark

Authors

PSPedro Miguel Sánchez SánchezUniversidad de Murcia EBEnrique Tomás Martínez BeltránUniversidad de Murcia CFChao Feng

Discussion

Member takes

Implication

Proposed client selection method shows improved model performance in decentralized federated learning, indicating enhanced efficiency in heterogeneous data environments.

Key Points

This work aims to improve client selection in decentralized federated learning while addressing challenges with non-IID data.
Proposes S-VOTE, a voting-based client selection mechanism.
Focused on optimizing resource usage and model performance.
Adopts an adaptive strategy to support local training and address participation imbalance.
Conducted extensive experiments on benchmark datasets.
Achieved up to 21% reduction in communication costs.
Demonstrated 4-6% faster convergence rates.
Improved local performance by 9-17% over baseline methods in certain configurations.
Reduced energy consumption by 14-24%.

Cite This Study

Sánchez et al. (2025) studied this question.

synapsesocial.com/papers/698c1bdc267fb587c655dca2 https://doi.org/10.5167/uzh-291150

View Full Paper

Ask AI

Bookmark

Implication

Proposed client selection method shows improved model performance in decentralized federated learning, indicating enhanced efficiency in heterogeneous data environments.

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

Discussion

Member takes

Implication

Key Points

Cite This Study

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

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider