Skip to main content

SimpleGAN: Stabilizing generative adversarial networks with simple distributions

Publication ,  Conference
Zhang, S; Qian, Z; Huang, K; Zhang, R; Hussain, A
Published in: IEEE International Conference on Data Mining Workshops, ICDMW
November 1, 2019

Generative Adversarial Networks (GANs) are powerful generative models, but usually suffer from hard training and poor generation. Due to complex data and generation distributions in high dimensional space, it is difficult to measure the departure of two distributions, which is however vital for training successful GANs. Previous methods try to alleviate this problem by choosing reasonable divergence metrics. Unlike previous methods, in this paper, we propose a novel method called SimpleGAN to tackle this problem: transform original complex distributions to simple ones in the low dimensional space while keeping information and then measure the departure of two simple distributions. This novel method offers a new direction to tackle the stability of GANs. Specifically, starting from maximization of the mutual information between variables in the original high dimensional space and low dimensional space, we eventually derive to optimize a much simplified version, i.e. the lower bound of the mutual information. For experiments, we implement our proposed method on different baselines i.e. traditional GAN, WGAN-GP and DCGAN for CIFAR-10 dataset. Our proposed method achieves obvious improvement over these baseline models.

Duke Scholars

Published In

IEEE International Conference on Data Mining Workshops, ICDMW

DOI

EISSN

2375-9259

ISSN

2375-9232

ISBN

9781728146034

Publication Date

November 1, 2019

Volume

2019-November

Start / End Page

905 / 910
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zhang, S., Qian, Z., Huang, K., Zhang, R., & Hussain, A. (2019). SimpleGAN: Stabilizing generative adversarial networks with simple distributions. In IEEE International Conference on Data Mining Workshops, ICDMW (Vol. 2019-November, pp. 905–910). https://doi.org/10.1109/ICDMW.2019.00132
Zhang, S., Z. Qian, K. Huang, R. Zhang, and A. Hussain. “SimpleGAN: Stabilizing generative adversarial networks with simple distributions.” In IEEE International Conference on Data Mining Workshops, ICDMW, 2019-November:905–10, 2019. https://doi.org/10.1109/ICDMW.2019.00132.
Zhang S, Qian Z, Huang K, Zhang R, Hussain A. SimpleGAN: Stabilizing generative adversarial networks with simple distributions. In: IEEE International Conference on Data Mining Workshops, ICDMW. 2019. p. 905–10.
Zhang, S., et al. “SimpleGAN: Stabilizing generative adversarial networks with simple distributions.” IEEE International Conference on Data Mining Workshops, ICDMW, vol. 2019-November, 2019, pp. 905–10. Scopus, doi:10.1109/ICDMW.2019.00132.
Zhang S, Qian Z, Huang K, Zhang R, Hussain A. SimpleGAN: Stabilizing generative adversarial networks with simple distributions. IEEE International Conference on Data Mining Workshops, ICDMW. 2019. p. 905–910.

Published In

IEEE International Conference on Data Mining Workshops, ICDMW

DOI

EISSN

2375-9259

ISSN

2375-9232

ISBN

9781728146034

Publication Date

November 1, 2019

Volume

2019-November

Start / End Page

905 / 910