FedUA: An Uncertainty-Aware Distillation-Based Federated Learning Scheme for Image Classification

FedUA: An Uncertainty-Aware Distillation-Based Federated Learning Scheme for Image Classification

Recently, federated learning (FL) has gradually become an important research topic in machine learning and information theory. FL emphasizes that clients jointly engage in solving learning tasks. In addition to data security issues, fundamental challenges in this type of learning include the imbalan...

Full description

Bibliographic Details
Main Authors: Shao-Ming Lee, Ja-Ling Wu
Format: Article
Language:English
Published: MDPI AG 2023-04-01
Series:Information
Subjects:
federated learning
model aggregation
knowledge distillation
uncertainty in deep neural networks
Online Access:https://www.mdpi.com/2078-2489/14/4/234

Internet

https://www.mdpi.com/2078-2489/14/4/234

Similar Items