FedPLT assigns client-specific model layers for training and matches or beats full-model federated learning accuracy with 71-82 percent fewer trainable parameters per client.
Federated dropout—a simple ap- proach for enabling federated learning on resource constrained devices,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training
FedPLT assigns client-specific model layers for training and matches or beats full-model federated learning accuracy with 71-82 percent fewer trainable parameters per client.