An autoencoder-based gradient compression scheme for federated learning that decodes the aggregated update directly, with claims of privacy and reduced communication that are only weakly supported.
1 -bit stochastic gradient descent and application to data-parallel distributed trai ning of speech DNNs,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
An End-to-End Encrypted Neural Network for Gradient Updates Transmission in Federated Learning
An autoencoder-based gradient compression scheme for federated learning that decodes the aggregated update directly, with claims of privacy and reduced communication that are only weakly supported.