Communication Efficient Federated Learning With Quantization-Aware Training Design

Model quantization is an effective method that can improve communication efficiency in federated learning (FL). The existing FL quantization protocols almost stay at the level of post-training quantization (PTQ), which comes at the cost of large quantization loss, especially in the setting of low-bi...

Descrición completa

Detalles Bibliográficos

Principais autores:	Xiang Fang, Li Chen, Huarui Yin, Xiaohui Chen, Weidong Wang
Formato:	Artigo
Idioma:	Inglês
Publicado:	IEEE 2026-01-01
Series:	IEEE Transactions on Machine Learning in Communications and Networking
Assuntos:	Federated learning quantization-aware learning non-uniform quantization post-training quantization adaptive-bits quantization
Acceso en liña:	https://ieeexplore.ieee.org/document/11260453/
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!