A semi-asynchronous federated graph learning framework with soft-label clustering, staleness-weighted aggregation, and cluster broadcasting reports higher accuracy and faster convergence than ten baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FedSA-GCL: A Semi-Asynchronous Federated Graph Learning Framework with Personalized Aggregation and Cluster-Aware Broadcasting
A semi-asynchronous federated graph learning framework with soft-label clustering, staleness-weighted aggregation, and cluster broadcasting reports higher accuracy and faster convergence than ten baselines.