SemiDFL is a semi-supervised decentralized federated learning method that uses neighborhood pseudo-labels, consensus-based diffusion-generated data, and adaptive aggregation to handle mixed labeled and unlabeled clients.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SemiDFL: A Semi-Supervised Paradigm for Decentralized Federated Learning
SemiDFL is a semi-supervised decentralized federated learning method that uses neighborhood pseudo-labels, consensus-based diffusion-generated data, and adaptive aggregation to handle mixed labeled and unlabeled clients.