Rate distortion optimization for adaptive gradient quantization in federated learning

Federated Learning (FL) is an emerging machine learning framework designed to preserve privacy. However, the continuous updating of model parameters over uplink channels with limited throughput leads to a huge communication overload, which is a major challenge for FL. To address this issue, we propo...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Guojun Chen, Kaixuan Xie, Wenqiang Luo, Yinfei Xu, Lun Xin, Tiecheng Song, Jing Hu
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	KeAi Communications Co., Ltd. 2024-12-01
Serie:	Digital Communications and Networks
Soggetti:	Federated learning Communication efficiency Adaptive quantization Rate distortion
Accesso online:	http://www.sciencedirect.com/science/article/pii/S235286482400018X
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!