Generative Adversarial Networks with Joint Distribution Moment Matching

doi:10.1007/s40305-019-00248-x

Journal of the Operations Research Society of China ›› 2019, Vol. 7 ›› Issue (4): 579-597.doi: 10.1007/s40305-019-00248-x

Special Issue: Continuous Optimization

Previous Articles Next Articles

Generative Adversarial Networks with Joint Distribution Moment Matching

Yi-Ying Zhang¹, Chao-Min Shen^1,2,3, Hao Feng⁴, Preston Thomas Fletcher⁵, Gui-Xu Zhang¹

1 Department of Computer Science, East China Normal University, Shanghai 200062, China;
2 Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200062, China;
3 Westlake Institute for Brain-Like Science and Technology, Hangzhou 310027, China;
4 Didi Chuxing Science and Technology Co. Ltd., Beijing 100193, China;
5 Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA 22904, USA

Received:2018-11-02 Revised:2019-03-27 Online:2019-11-30 Published:2019-11-28
Contact: Chao-Min Shen, Yi-Ying Zhang, Hao Feng, Preston Thomas Fletcher, Gui-Xu Zhang E-mail:cmshen@cs.ecnu.edu.cn;yyzhangcs@outlook.com;fengxhao@outlook.com;ptf8v@virginia.edu;gxzhang@cs.ecnu.edu.cn
Supported by:
This work is supported by the National Natural Science Foundation of China (Nos. 11771276, 11471208, 61731009), and the Foundation of Science and Technology Commission of Shanghai Municipality (No. 14DZ2260800).

Abstract

Abstract: Generative adversarial networks (GANs) have shown impressive power in the field of machine learning. Traditional GANs have focused on unsupervised learning tasks. In recent years, conditional GANs that can generate data with labels have been proposed in semi-supervised learning and have achieved better image quality than traditional GANs. Conditional GANs, however, generally only minimize the difference between marginal distributions of real and generated data, neglecting the difference with respect to each class of the data. To address this challenge, we propose the GAN with joint dis tribution moment matching (JDMM-GAN) for matching the joint distribution based on maximum mean discrepancy, which minimizes the differences of both the marginal and conditional distributions. The learning procedure is iteratively conducted by the stochastic gradient descent and back-propagation. We evaluate JDMM-GAN on several benchmark datasets, including MNIST, CIFAR-10 and the Extended Yale Face. Compared with the state-of-the-art GANs, JDMM-GAN generates more realistic images and achieves the best inception score for CIFAR-10 dataset.

Key words: Generative Adversarial Networks, Joint Distribution Moment Matching, Maximum mean discrepancy

CLC Number:

68T45
62P99

Yi-Ying Zhang, Chao-Min Shen, Hao Feng, Preston Thomas Fletcher, Gui-Xu Zhang. Generative Adversarial Networks with Joint Distribution Moment Matching[J]. Journal of the Operations Research Society of China, 2019, 7(4): 579-597.

TrendMD

References

[1] Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.:Generative adversarial nets. In:Advances in Neural Information Processing Systems, pp. 2672-2680(2014)
[2] Manisha, P., Gujar, S.:Generative adversarial networks (gans):What it can generate and what it cannot?. arXiv:1804.00140(2018)
[3] Arjovsky, M., Chintala, S., Bottou, L.:Wasserstein GAN. arXiv:1701.07875(2017)
[4] Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.:Improved training of Wasserstein GANs. arXiv:1704.00028(2017)
[5] Radford, A., Metz, L., Chintala, S.:Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434(2015)
[6] Denton, E.L., Chintala, S., Fergus, R., et al.:Deep generative image models using a Laplacian pyramid of adversarial networks. In:Advances in Neural Information Processing Systems, pp. 1486-1494(2015)
[7] Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al.:Photo-realistic single image super-resolution using a generative adversarial network. arXiv:1609.04802(2016)
[8] Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.:Generative adversarial text to image synthesis. arXiv:1605.05396(2016)
[9] Li, Y., Swersky, K., Zemel, R.:Generative moment matching networks. In:Proceedings of the 32nd International Conference on Machine Learning, pp. 1718-1727(2015)
[10] Dziugaite,G.K.,Roy,D.M.,Ghahramani,Z.:Training generativeneuralnetworksviamaximum mean discrepancy optimization. arXiv:1505.03906(2015)
[11] Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.:A kernel two-sample test. J. Mach. Learn. Res. 13(3), 723-773(2012)
[12] van den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A., et al.:Conditional image generation with PixelCNN decoders. In:Advances in Neural Information Processing Systems, pp. 4790-4798(2016)
[13] Mirza, M., Osindero, S.:Conditional generative adversarial nets. arXiv:1411.1784(2014)
[14] Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.:Infogan:interpretable representationlearningbyinformationmaximizinggenerativeadversarialnets.In:AdvancesinNeural Information Processing Systems, pp. 2172-2180(2016)
[15] Zhao, J., Mathieu, M., LeCun, Y.:Energy-based generative adversarial network. arXiv:1609.03126(2016)
[16] Feng, H., Peng, Y., Zhang, G., Shen, C.:Joint distribution adaptation based TSK fuzzy logic system for epileptic EEG signal identification. In:IEEE International Conference on Bioinformatics and Biomedicine, pp. 340-345(2016)
[17] Ren, Y., Zhu, J., Li, J., Luo, Y.:Conditional generative moment-matching networks. In:Advances in Neural Information Processing Systems, pp. 2928-2936(2016)
[18] Sutherland, D.J., Tung, H.Y., Strathmann, H., De, S., Ramdas, A., Smola, A., Gretton, A.:Generative models and model criticism via optimized maximum mean discrepancy. arXiv:1611.04488(2016)
[19] Wasserman, L.:All of Statistics:a Concise Course in Statistical Inference. Springer, Berlin (2013)
[20] Li, C.L., Chang, W.C., Cheng, Y., Yang, Y., Póczos, B.:MMD GAN:Towards deeper understanding of moment matching network. arXiv:1705.08584(2017)
[21] Long, M., Wang, J., Ding, G., Pan, S.J., Yu, P.S.:Adaptation regularization:a general framework for transfer learning. IEEE Trans. Knowl. Data Eng. 26(5), 1076-1089(2014)
[22] Odena, A., Olah, C., Shlens, J.:Conditional image synthesis with auxiliary classifier GANs. arXiv:1610.09585(2016)
[23] LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.:Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278-2324(1998)
[24] Krizhevsky, A.:Learning multiple layers of features from tiny images. Tech. rep., University of Toronto (2009)
[25] Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.:From few to many:illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intell. 23(6), 643-660(2001)
[26] Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.:Improved techniques for training GANs. In:Advances in Neural Information Processing Systems, pp. 2234-2242(2016)
[27] Fukumizu, K., Gretton, A., Lanckriet, G.R., Schölkopf, B., Sriperumbudur, B.K.:Kernel choice and classifiability for RKHS embeddings of probability distributions. In:Advances in Neural Information Processing Systems, pp. 1750-1758(2009)
[28] Gretton, A., Sejdinovic, D., Strathmann, H., Balakrishnan, S., Pontil, M., Fukumizu, K., Sriperumbudur, B.K.:Optimal kernel choice for large-scale two-sample tests. In:Advances in Neural Information Processing Systems, pp. 1205-1213(2012)
[29] Kingma, D., Ba, J.:Adam:a method for stochastic optimization. arXiv:1412.6980(2014)
[30] Wang, D., Liu, Q.:Learning to draw samples:With application to amortized MLE for generative adversarial learning. arXiv:1611.01722(2016)

Generative Adversarial Networks with Joint Distribution Moment Matching

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 0

Recommended Articles

Metrics

Comments