GCFL applies a gradient projection correction on the server to noisy differentially private client gradients and claims improved accuracy under the same privacy budget.
Differential evolution with joint adaptation of mutation strategies and control parameters via distributed proximal policy optimization,
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
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
GCFL: A Gradient Correction-based Federated Learning Framework for Privacy-preserving CPSS
GCFL applies a gradient projection correction on the server to noisy differentially private client gradients and claims improved accuracy under the same privacy budget.