Advertisement

Fictitious GAN: Training GANs with Historical Models

  • Hao GeEmail author
  • Yin Xia
  • Xu Chen
  • Randall Berry
  • Ying Wu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11205)

Abstract

Generative adversarial networks (GANs) are powerful tools for learning generative models. In practice, the training may suffer from lack of convergence. GANs are commonly viewed as a two-player zero-sum game between two neural networks. Here, we leverage this game theoretic view to study the convergence behavior of the training process. Inspired by the fictitious play learning process, a novel training method, referred to as Fictitious GAN, is introduced. Fictitious GAN trains the deep neural networks using a mixture of historical models. Specifically, the discriminator (resp. generator) is updated according to the best-response to the mixture outputs from a sequence of previously trained generators (resp. discriminators). It is shown that Fictitious GAN can effectively resolve some convergence issues that cannot be resolved by the standard training approach. It is proved that asymptotically the average of the generator outputs has the same distribution as the data samples.

Supplementary material

474172_1_En_8_MOESM1_ESM.pdf (215 kb)
Supplementary material 1 (pdf 214 KB)

References

  1. 1.
    Arora, S., Ge, R., Liang, Y., Ma, T., Zhang, Y.: Generalization and equilibrium in generative adversarial nets (GANs). In: International Conference on Machine Learning, pp. 224–232 (2017)Google Scholar
  2. 2.
    Brown, G.W.: Iterative solution of games by fictitious play. Act. Anal. Prod. Alloc. 13(1), 374–376 (1951)MathSciNetzbMATHGoogle Scholar
  3. 3.
    Che, T., Li, Y., Jacob, A.P., Bengio, Y., Li, W.: Mode regularized generative adversarial networks. In: Proceedings of International Conference on Learning Representations (2017)Google Scholar
  4. 4.
    Chen, X., Wang, J., Ge, H.: Training generative adversarial networks via primal-dual subgradient methods: a Lagrangian perspective on GAN. In: Proceedings of International Conference on Learning Representations (2018)Google Scholar
  5. 5.
    Danskin, J.M.: Fictitious play for continuous games. Nav. Res. Logist. (NRL) 1(4), 313–320 (1954)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Durugkar, I., Gemp, I., Mahadevan, S.: Generative multi-adversarial networks. arXiv preprint arXiv:1611.01673 (2016)
  7. 7.
    Ghosh, A., Kulharia, V., Namboodiri, V., Torr, P.H., Dokania, P.K.: Multi-agent diverse generative adversarial networks. arXiv preprint arXiv:1704.02906 (2017)
  8. 8.
    Goodfellow, I.: Nips 2016 tutorial: generative adversarial networks. arXiv preprint arXiv:1701.00160 (2016)
  9. 9.
    Chen, M., Denoyer, L.: Multi-view generative adversarial networks. In: Ceci, M., Hollmén, J., Todorovski, L., Vens, C., Džeroski, S. (eds.) ECML PKDD 2017. LNCS, vol. 10535, pp. 175–188. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-71246-8_11CrossRefGoogle Scholar
  10. 10.
    Grnarova, P., Levy, K.Y., Lucchi, A., Hofmann, T., Krause, A.: An online learning approach to generative adversarial networks. In: Proceedings of International Conference on Learning Representations (2018)Google Scholar
  11. 11.
    Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6626–6637 (2017)Google Scholar
  12. 12.
    Hoang, Q., Nguyen, T.D., Le, T., Phung, D.: Multi-generator gernerative adversarial nets. arXiv preprint arXiv:1708.02556 (2017)
  13. 13.
    Huang, X., Li, Y., Poursaeed, O., Hopcroft, J., Belongie, S.: Stacked generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, p. 4 (2017)Google Scholar
  14. 14.
    Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46475-6_43CrossRefGoogle Scholar
  15. 15.
    Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 105–114 (2017)Google Scholar
  16. 16.
    Li, J., Madry, A., Peebles, J., Schmidt, L.: Towards understanding the dynamics of generative adversarial networks. arXiv preprint arXiv:1706.09884 (2017)
  17. 17.
    Metz, L., Poole, B., Pfau, D., Sohl-Dickstein, J.: Unrolled generative adversarial networks. In: Proceedings of International Conference on Learning Representations (2017)Google Scholar
  18. 18.
    Nagarajan, V., Kolter, J.Z.: Gradient descent GAN optimization is locally stable. In: Advances in Neural Information Processing Systems, pp. 5585–5595 (2017)Google Scholar
  19. 19.
    Nguyen, T., Le, T., Vu, H., Phung, D.: Dual discriminator generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2667–2677 (2017)Google Scholar
  20. 20.
    Nowozin, S., Cseke, B., Tomioka, R.: f-GAN: training generative neural samplers using variational divergence minimization. In: Advances in Neural Information Processing Systems, pp. 271–279 (2016)Google Scholar
  21. 21.
    Oliehoek, F.A., Savani, R., Gallego, J., van der Pol, E., Gross, R.: Beyond local nash equilibria for adversarial networks. arXiv preprint arXiv:1806.07268 (2018)
  22. 22.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: Proceedings of International Conference on Learning Representations (2016)Google Scholar
  23. 23.
    Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning, pp. 1060–1069 (2016)Google Scholar
  24. 24.
    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)Google Scholar
  25. 25.
    Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 3, p. 6 (2017)Google Scholar
  26. 26.
    Sion, M.: On general minimax theorems. Pac. J. Math. 8(1), 171–176 (1958)MathSciNetCrossRefGoogle Scholar
  27. 27.
    Tolstikhin, I.O., Gelly, S., Bousquet, O., Simon-Gabriel, C.J., Schölkopf, B.: ADAGAN: boosting generative models. In: Advances in Neural Information Processing Systems, pp. 5424–5433 (2017)Google Scholar
  28. 28.
    Zhai, S., Cheng, Y., Lu, W., Zhang, Z.: Deep structured energy based models for anomaly detection. In: International Conference on Machine Learning, pp. 1100–1109 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Hao Ge
    • 1
    Email author
  • Yin Xia
    • 1
  • Xu Chen
    • 1
  • Randall Berry
    • 1
  • Ying Wu
    • 1
  1. 1.Northwestern UniversityEvanstonUSA

Personalised recommendations