How the generative adversarial network is trained using a federated learning framework. (IMAGE)

Intelligent Computing

How the generative adversarial network is trained using a federated learning framework.

Caption

During training, only the parameters of the generator are transmitted between the central server and local devices. The discriminators on the local devices update their regularization terms based on the parameters received from the server.

Credit

YIYU GUO ET AL.

Usage Restrictions

Credit must be given to the creator.

License

CC BY

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.