Privacy-Enhanced Federated Learning for Non-IID Data

Privacy-Enhanced Federated Learning for Non-IID Data

Federated learning (FL) allows the collaborative training of a collective model by a vast number of decentralized clients while ensuring that these clients’ data remain private and are not shared. In practical situations, the training data utilized in FL often exhibit non-IID characteristics, hence...

Full description

Bibliographic Details
Main Authors: Qingjie Tan, Shuhui Wu, Yuanhong Tao
Format: Article
Language:English
Published: MDPI AG 2023-09-01
Series:Mathematics
Subjects:
federated learning
Hellinger distance
differential privacy
non-IID data
Online Access:https://www.mdpi.com/2227-7390/11/19/4123

Internet

https://www.mdpi.com/2227-7390/11/19/4123

Similar Items