eduzhai > Applied Sciences > Engineering >

Learn distributed GAN with Temporary Discriminators

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 22 pages

Abstract: In this work, we propose a method for training distributed GAN withsequential temporary discriminators. Our proposed method tackles the challengeof training GAN in the federated learning manner: How to update the generatorwith a flow of temporary discriminators? We apply our proposed method to learna self-adaptive generator with a series of local discriminators from multipledata centers. We show our design of loss function indeed learns the correctdistribution with provable guarantees. The empirical experiments show that ourapproach is capable of generating synthetic data which is practical forreal-world applications such as training a segmentation model.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×