FedGloSS optimizes global sharpness on the server using the previous pseudo-gradient to approximate SAM's perturbation, achieving better accuracy and flatness in heterogeneous federated learning without extra communication.
Window-based model averaging improves generalization in heterogeneous federated learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning
FedGloSS optimizes global sharpness on the server using the previous pseudo-gradient to approximate SAM's perturbation, achieving better accuracy and flatness in heterogeneous federated learning without extra communication.