Generative adversarial networks (GANs) have been effective for learning generative models for real-world data. However, accompanied with the generative tasks becoming more and more challenging, existing GANs (GAN and its variants) tend to suffer from different training problems such as instability and mode collapse. In this paper, we propose a novel GAN framework called evolutionary GANs (E-GANs) for stable GAN training and improved generative performance. Unlike existing GANs, which employ a predefined adversarial objective function alternately training a generator and a discriminator, we evolve a population of generators to play the adversarial game with the discriminator. Different adversarial training objectives are employed as mutation operations and each individual (i.e., generator candidature) are updated based on these mutations. Then, we devise an evaluation mechanism to measure the quality and diversity of generated samples, such that only well-performing generator(s) are preserved and used for further training. In this way, E-GAN overcomes the limitations of an individual adversarial training objective and always preserves the well-performing offspring, contributing to progress in, and the success of GANs. Experiments on several datasets demonstrate that E-GAN achieves convincing generative performance and reduces the training problems inherent in existing GANs. © 1997-2012 IEEE.
Bibliographical noteThis work was supported in part by the Australian Research Council under Project FL-170100117, Project DP-180103424, Project IH180100002, and Project DE180101438, in part by the National Key Research and Development Program of China under Grant 2017YFC0804003, in part by the Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/J017515/1 and Grant EP/P005578/1, in part by the Program for Guangdong Introducing Innovative and Enterpreneurial Teams under Grant 2017ZT07X386, in part by the Shenzhen Peacock Plan under Grant KQTD2016112514355531, in part by the Science and Technology Innovation Committee Foundation of Shenzhen under Grant ZDSYS201703031748284, and in part by the Program for University Key Laboratory of Guangdong Province under Grant 2017KSYS008.
- Deep generative models
- evolutionary computation
- generative adversarial networks (GANs)