Distributed Generative Adversarial Net
This work addresses privacy concerns in distributed AI training for users in multi-user settings, but it appears incremental as it builds on existing GAN frameworks.
The paper tackles the problem of training Generative Adversarial Networks (GANs) in multi-user environments by proposing Distributed-GAN, which allows users to train locally with their own data to generate more diverse samples without sharing data, thereby avoiding privacy leakage.
Recently the Generative Adversarial Network has become a hot topic. Considering the application of GAN in multi-user environment, we propose Distributed-GAN. It enables multiple users to train with their own data locally and generates more diverse samples. Users don't need to share data with each other to avoid the leakage of privacy. In recent years, commercial companies have launched cloud platforms based on artificial intelligence to provide model for users who lack computing power. We hope our work can inspire these companies to provide more powerful AI services.