Communication-Efficient Design for Quantized Decentralized Federated Learning
(2024)
Journal Article
Decentralized federated learning (DFL) is a variant of federated learning, where edge nodes only communicate with their one-hop neighbors to learn the optimal model. However, as information exchange is restricted in a range of one-hop in DFL, ineffic... Read More about Communication-Efficient Design for Quantized Decentralized Federated Learning.