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...

Szczegółowa specyfikacja

Opis bibliograficzny

Główni autorzy:	Xiang Fang, Li Chen, Huarui Yin, Xiaohui Chen, Weidong Wang
Format:	Artigo
Język:	Inglês
Wydane:	IEEE 2026-01-01
Seria:	IEEE Transactions on Machine Learning in Communications and Networking
Hasła przedmiotowe:	Federated learning quantization-aware learning non-uniform quantization post-training quantization adaptive-bits quantization
Dostęp online:	https://ieeexplore.ieee.org/document/11260453/
Etykiety:	Dodaj etykietę Nie ma etykietki, Dołącz pierwszą etykiete!