SMRFL applies sharpness-aware minimization to federated learning for robustness to model perturbations, but the central convergence theorem is invalid as stated.
Byzantine-resilient secure federated learning,
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
-
Robust Federated Learning against Model Perturbation in Edge Networks
SMRFL applies sharpness-aware minimization to federated learning for robustness to model perturbations, but the central convergence theorem is invalid as stated.