FedAPM applies ADMM with first- and second-order proximal corrections to partial model personalization in federated learning, proving global convergence and reporting better accuracy, F1, and AUC than FedAlt, FedSim, FedAvg, and FedProx.
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
-
FedAPM: Federated Learning via ADMM with Partial Model Personalization
FedAPM applies ADMM with first- and second-order proximal corrections to partial model personalization in federated learning, proving global convergence and reporting better accuracy, F1, and AUC than FedAlt, FedSim, FedAvg, and FedProx.