A federated learning scheme that compresses client gradients with truncated SVD or Tucker decomposition and then quantizes the components, cutting transmitted bits by about 90 to 97 percent at some accuracy cost.
Federated learning in mobile edge networks: A com- prehensive survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Quantized Rank Reduction: A Communications-Efficient Federated Learning Scheme for Network-Critical Applications
A federated learning scheme that compresses client gradients with truncated SVD or Tucker decomposition and then quantizes the components, cutting transmitted bits by about 90 to 97 percent at some accuracy cost.