IFL-GAN: Improved Federated Learning Generative Adversarial Network With Maximum Mean Discrepancy Model Aggregation

The generative adversarial network (GAN) is usually built from the centralized, independent identically distributed (i.i.d.) training data to generate realistic-like instances. In real-world applications, however, the data may be distributed over multiple clients and hard to be gathered due to bandw...

Full description

Bibliographic Details

Published in:	IEEE transaction on neural networks and learning systems Vol. 34; no. 12; pp. 10502 - 10515
Main Authors:	Li, Wei, Chen, Jinlin, Wang, Zhenyu, Shen, Zhidong, Ma, Chao, Cui, Xiaohui
Format:	Journal Article
Language:	English
Published:	United States IEEE 01.12.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Collaborative work Computational modeling Convergence Data models Distributed databases Federated learning generative adversarial network (GAN) Generative adversarial networks Machine learning maximum mean discrepancy (MMD) non-independent identically distributed (i.i.d.) training data Training Training data
ISSN:	2162-237X, 2162-2388, 2162-2388
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!