Optimizing Multi-Objective Federated Learning on Non-IID Data with Improved NSGA-III and Hierarchical Clustering

Optimizing Multi-Objective Federated Learning on Non-IID Data with Improved NSGA-III and Hierarchical Clustering

Federated learning (FL) can tackle the problem of data silos of asymmetric information and privacy leakage; however, it still has shortcomings, such as data heterogeneity, high communication cost and uneven distribution of performance. To overcome these issues and achieve parameter optimization of F...

Full description

Bibliographic Details
Main Authors: Jialin Zhong, Yahui Wu, Wubin Ma, Su Deng, Haohao Zhou
Format: Article
Language:English
Published: MDPI AG 2022-05-01
Series:Symmetry
Subjects:
federated learning
multi-objective optimization
NSGA-III
parameter optimization
Online Access:https://www.mdpi.com/2073-8994/14/5/1070

Similar Items

Similar Items