S-VOTE selects clients by cosine similarity of model weights and lets low-vote clients sometimes skip training, reducing communication and energy while improving non-IID accuracy in some settings.
Decentralized personalized federated learning: Lower bounds and optimal algorithm for all per- sonalization modes,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
S-VOTE: Similarity-based Voting for Client Selection in Decentralized Federated Learning
S-VOTE selects clients by cosine similarity of model weights and lets low-vote clients sometimes skip training, reducing communication and energy while improving non-IID accuracy in some settings.