Abstract
Generative adversarial network (GAN) is an implicit generative model known for its ability to generate sharp images. However, it is poor at generating diverse data, which refers to the mode collapse problem. It turns out that GAN is prone to emphasizing the quality of samples but ignoring their diversity. When mode collapse happens, the support of the generated data distribution is not aligned with that of the real data distribution. We thus propose Support Regularized-GAN (SR-GAN) to address such a mode collapse issue by matching their support. Our experiments on synthetic and real-world datasets show that our regularization can mitigate the mode collapse and also improve the data quality.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. In: ICLR (2017)
Du, C., Xu, K., Li, C., Zhu, J., Zhang, B.: Learning implicit generative models by teaching explicit ones. In: arXiv (2018)
Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS, pp. 2672–2680 (2014)
Görnitz, N., Lima, L.A., Müller, K., Kloft, M., Nakajima, S.: Support vector data descriptions and \(k\)-means clustering: one class? TNNLS 29, 3994–4006 (2018)
Hu, W., Miyato, T., Tokui, S., Matsumoto, E., Sugiyama, M.: Learning discrete representations via information maximizing self-augmented training. In: ICML, pp. 1558–1567 (2017)
Li, C., Alvarez-Melis, D., Xu, K., Jegelka, S., Sra, S.: Distributional adversarial networks. In: ICLR (2018)
Metz, L., Poole, B., Pfau, D., Sohl-Dickstein, J.: Unrolled generative adversarial networks. In: ICLR (2017)
Schölkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Neural Comput. 13(7), 1443–1471 (2001)
Srivastava, A., Valkov, L., Russell, C., Gutmann, M.U., Sutton, C.: VEEGAN: reducing mode collapse in gans using implicit variational learning. In: NeurIPS, pp. 3308–3318 (2017)
Tax, D.M., Duin, R.P.: Support vector data description. Mach. Learn. 54(1), 45–66 (2004)
Acknowledgement
This work was supported by the National Key R&D Program of China (Grant No. 2017YFC0804003), the Program for Guangdong Introducing Innovative and Enterpreneurial Teams (Grant No. 2017ZT07X386), Shenzhen Peacock Plan (Grant No. KQTD2016112514355531), the Program for University Key Laboratory of Guangdong Province (Grant No. 2017KSYS008), and Australian Research Council (Grant No. LP150100671 and No. DP180100106).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Yao, Y., Pan, Y., Tsang, I.W., Yao, X. (2019). Support Matching: A Novel Regularization to Escape from Mode Collapse in GANs. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1142. Springer, Cham. https://doi.org/10.1007/978-3-030-36808-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-36808-1_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36807-4
Online ISBN: 978-3-030-36808-1
eBook Packages: Computer ScienceComputer Science (R0)