A hierarchical federated learning framework with gradient sparsification reduces modeled communication latency in heterogeneous cellular networks while keeping CIFAR-10 accuracy close to a flat baseline.
Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Cooperative training methods for distributed machine learning typically assume noiseless and ideal communication channels. This work studies some of the opportunities and challenges arising from the presence of wireless communication links. We specifically consider wireless implementations of Federated Learning (FL) and Federated Distillation (FD), as well as of a novel Hybrid Federated Distillation (HFD) scheme. Both digital implementations based on separate source-channel coding and over-the-air computing implementations based on joint source-channel coding are proposed and evaluated over Gaussian multiple-access channels.
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Hierarchical Federated Learning Across Heterogeneous Cellular Networks
A hierarchical federated learning framework with gradient sparsification reduces modeled communication latency in heterogeneous cellular networks while keeping CIFAR-10 accuracy close to a flat baseline.