Communication-efficient federated learning via knowledge distillation

Federated learning is a privacy-preserving machine learning technique to train intelligent models from decentralized data, which enables exploiting private data by communicating local model updates in each iteration of model learning rather than the raw data. However, model updates can be extremely...

Descripción completa

Detalles Bibliográficos
Autores principales: Wu, Chuhan, Wu, Fangzhao, Lyu, Lingjuan, Huang, Yongfeng, Xie, Xing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9018897/
https://www.ncbi.nlm.nih.gov/pubmed/35440643
http://dx.doi.org/10.1038/s41467-022-29763-x

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9018897/
https://www.ncbi.nlm.nih.gov/pubmed/35440643
http://dx.doi.org/10.1038/s41467-022-29763-x

Ejemplares similares