A federated-learning gradient compressor that sends tiny synthetic features instead of gradients, plus a download-phase compressor and a budget scheduler, with conditional convergence proofs and broad experiments.
Communication- efficient federated learning with single-step synthetic features compres- sor for faster convergence,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
extension 1polarities
extend 1representative citing papers
citing papers explorer
-
E-3SFC: Communication-Efficient Federated Learning with Double-way Features Synthesizing
A federated-learning gradient compressor that sends tiny synthetic features instead of gradients, plus a download-phase compressor and a budget scheduler, with conditional convergence proofs and broad experiments.