Adding MMD regularization or feature fusion modules to on-device training can reduce federated learning communication rounds by 20-60 percent on MNIST and CIFAR-10, according to the authors' experiments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Federated Learning with Additional Mechanisms on Clients to Reduce Communication Costs
Adding MMD regularization or feature fusion modules to on-device training can reduce federated learning communication rounds by 20-60 percent on MNIST and CIFAR-10, according to the authors' experiments.