Learn distributed GAN with Temporary Discriminators
This addresses the problem of distributed GAN training for applications such as medical imaging, though it appears incremental as it builds on existing federated learning and GAN frameworks.
The paper tackles the challenge of training GANs in a federated learning setting by proposing a method with sequential temporary discriminators, showing provable guarantees for learning the correct distribution and generating synthetic data practical for real-world applications like training segmentation models.
In this work, we propose a method for training distributed GAN with sequential temporary discriminators. Our proposed method tackles the challenge of training GAN in the federated learning manner: How to update the generator with a flow of temporary discriminators? We apply our proposed method to learn a self-adaptive generator with a series of local discriminators from multiple data centers. We show our design of loss function indeed learns the correct distribution with provable guarantees. The empirical experiments show that our approach is capable of generating synthetic data which is practical for real-world applications such as training a segmentation model.