A federated learning method that distills a universal model from cluster-specific models using data-free knowledge distillation and adaptive label weighting.
Swiftagg: Communication-efficient and dropout-resistant secure aggregation for federated learning with worst-case security guarantees
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
-
Distilling A Universal Expert from Clustered Federated Learning
A federated learning method that distills a universal model from cluster-specific models using data-free knowledge distillation and adaptive label weighting.