Learning Generative Adversarial Networks from Multiple Data Sources

Learning Generative Adversarial Networks from Multiple Data Sources

Trung Le, Quan Hoang, Hung Vu, Tu Dinh Nguyen, Hung Bui, Dinh Phung

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 2823-2829. https://doi.org/10.24963/ijcai.2019/391

Generative Adversarial Networks (GANs) are a powerful class of deep generative models. In this paper, we extend GAN to the problem of generating data that are not only close to a primary data source but also required to be different from auxiliary data sources. For this problem, we enrich both GANs' formulations and applications by introducing pushing forces that thrust generated samples away from given auxiliary data sources. We term our method Push-and-Pull GAN (P2GAN). We conduct extensive experiments to demonstrate the merit of P2GAN in two applications: generating data with constraints and addressing the mode collapsing problem. We use CIFAR-10, STL-10, and ImageNet datasets and compute Fr├ęchet Inception Distance to evaluate P2GAN's effectiveness in addressing the mode collapsing problem. The results show that P2GAN outperforms the state-of-the-art baselines. For the problem of generating data with constraints, we show that P2GAN can successfully avoid generating specific features such as black hair.
Keywords:
Machine Learning: Learning Generative Models
Machine Learning: Adversarial Machine Learning