A unified compression pipeline for federated learning delivers over 11x model size reduction and 60% faster training with a 2% accuracy drop on CIFAR-10 ResNet-12 under 2 Mbps bandwidth.
Communication efficiency in federated learning: Achievements and challenges
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Full Compression Pipeline for Green Federated Learning in Communication-Constrained Environments
A unified compression pipeline for federated learning delivers over 11x model size reduction and 60% faster training with a 2% accuracy drop on CIFAR-10 ResNet-12 under 2 Mbps bandwidth.