Efficient Gradient Updating Strategies with Adaptive Power Allocation for Federated Learning over Wireless Backhaul

In this paper, efficient gradient updating strategies are developed for the federated learning when distributed clients are connected to the server via a wireless backhaul link. Specifically, a common convolutional neural network (CNN) module is shared for all the distributed clients and it is train...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Yunji, Hong, Yonggi, Park, Jaehyun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8537050/
https://www.ncbi.nlm.nih.gov/pubmed/34696003
http://dx.doi.org/10.3390/s21206791

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8537050/
https://www.ncbi.nlm.nih.gov/pubmed/34696003
http://dx.doi.org/10.3390/s21206791

Ejemplares similares