Asynchronous probability ensembling allows heterogeneous CNNs to collaborate in federated disaster detection by exchanging class probabilities instead of weights, reducing communication and improving accuracy.
SCAFFOLD: Stochastic controlled averaging for federated learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Asynchronous Probability Ensembling for Federated Disaster Detection
Asynchronous probability ensembling allows heterogeneous CNNs to collaborate in federated disaster detection by exchanging class probabilities instead of weights, reducing communication and improving accuracy.
-
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.