pFedWN combines channel-aware neighbor selection with an EM-based model weighting step to personalize federated learning over server-free D2D wireless networks.
Towards provably personalized federated learning via threshold-clustering of similar clients,
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
background 1representative citing papers
citing papers explorer
-
pFedWN: A Personalized Federated Learning Framework for D2D Wireless Networks with Heterogeneous Data
pFedWN combines channel-aware neighbor selection with an EM-based model weighting step to personalize federated learning over server-free D2D wireless networks.