Privacy and distribution preserving generative adversarial networks with sample balancing

Differential privacy (DP) generative adversarial networks (GANs) can generate protected synthetic samples from downstream analysis. However, training on unbalanced datasets can bias the network towards majority classes, leading minority undertrained. Meanwhile, gradient perturbation in DP has no gua...

Full description

Bibliographic Details

Published in:	Expert systems with applications Vol. 258; p. 125181
Main Authors:	Sun, Haoran, Tang, Jinchuan, Dang, Shuping, Chen, Gaojie
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 15.12.2024
Subjects:	Data balancing Data-wise differential privacy Feature holding Generative adversarial networks Sample perturbation Sample perturbation Generative adversarial networks Data-wise differential privacy Data balancing Feature holding
ISSN:	0957-4174
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!