An adaptive mixed-resolution gradient quantizer plus uplink power control reduces federated learning communication overhead by over 90% while keeping test accuracy close to full-precision FL on CIFAR and Fashion-MNIST.
Communication-efficient Federated Learning with adap- tive quantization,
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Adaptive Quantization Resolution and Power Control for Federated Learning over Cell-free Networks
An adaptive mixed-resolution gradient quantizer plus uplink power control reduces federated learning communication overhead by over 90% while keeping test accuracy close to full-precision FL on CIFAR and Fashion-MNIST.