Data augmentation scheme for federated learning with non-IID data

Data augmentation scheme for federated learning with non-IID data

To solve the problem that the model accuracy remains low when the data are not independent and identically distributed (non-IID) across different clients in federated learning, a privacy-preserving data augmentation scheme was proposed.Firstly, a data augmentation framework for federated learning sc...

Full description

Saved in:
Bibliographic Details
Main Authors: Lingtao TANG, Di WANG, Shengyun LIU
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2023-01-01
Series:Tongxin xuebao
Subjects:
federated learning
Non-IID
generative adversarial network
differential privacy
data augmentation
Online Access:http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023007/
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items