Skip to main content
SpringerLink
Log in

VAEPP: Variational Autoencoder with a Pull-Back Prior

  • Conference paper
  • First Online:
Neural Information Processing (ICONIP 2020)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 12534))

Included in the following conference series:

Abstract

Many approaches to training generative models by distinct training objectives have been proposed in the past. Variational Autoencoder (VAE) is an outstanding model of them based on log-likelihood. In this paper, we propose a novel learnable prior, Pull-back Prior, for VAEs by adjusting the density of the prior through a discriminator that can assess the quality of data. It involves the discriminator from the theory of GANs to enrich the prior in VAEs. Based on it, we propose a more general framework, VAE with a Pull-back Prior (VAEPP), which uses existing techniques of VAEs and WGANs, to improve the log-likelihood, quality of sampling and stability of training. In MNIST and CIFAR-10, the log-likelihood of VAEPP outperforms models without autoregressive components and is comparable to autoregressive models. In MNIST, Fashion-MNIST, CIFAR-10 and CelebA, the FID of VAEPP is comparable to GANs and SOTA of VAEs.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Arjovsky, M., Chintala, S., et al.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223 (2017)

    Google Scholar 

  2. Bauer, M., Mnih, A.: Resampled priors for variational autoencoders. In: The 22nd International Conference on Artificial Intelligence and Statistics, pp. 66–75 (2019)

    Google Scholar 

  3. Chen, X., Mishra, N., et al.: PixelSNAIL: an improved autoregressive generative model. In: International Conference on Machine Learning, pp. 863–871 (2018)

    Google Scholar 

  4. Dai, B., Wipf, P.D.: Diagnosing and enhancing VAE models. In: ICLR (2019)

    Google Scholar 

  5. Gelfand, I.M., Silverman, R.A., et al.: Calculus of variations. Courier Corporation (2000)

    Google Scholar 

  6. Goodfellow, I., Pouget-Abadie, J., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)

    Google Scholar 

  7. Gulrajani, I., Ahmed, F., et al.: Improved training of Wasserstein GANs. In: NIPS (2017)

    Google Scholar 

  8. Heusel, M., Ramsauer, H., et al.: 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 

  9. Hoffman, M.D., Johnson, M.J.: Elbo surgery: yet another way to carve up the variational evidence lower bound. In: Workshop in Advances in Approximate Bayesian Inference, NIPS, vol. 1 (2016)

    Google Scholar 

  10. Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: ICLR (2014)

    Google Scholar 

  11. Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1 \(\times \) 1 convolutions. In: Advances in Neural Information Processing Systems, pp. 10215–10224 (2018)

    Google Scholar 

  12. Kingma, D.P., Salimans, T., et al.: Improved variational inference with inverse autoregressive flow. In: Advances in Neural Information Processing Systems, pp. 4743–4751 (2016)

    Google Scholar 

  13. Kumar, R., Goyal, A., et al.: Maximum entropy generators for energy-based models. arXiv preprint arXiv:1901.08508 (2019)

  14. Lake, B.M., Salakhutdinov, R., et al.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)

    Article  MathSciNet  Google Scholar 

  15. Larochelle, H., Murray, I.: The neural autoregressive distribution estimator. In: AISTATS, pp. 29–37 (2011)

    Google Scholar 

  16. Liu, Z., Luo, P., et al.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730–3738 (2015)

    Google Scholar 

  17. Maaløe, L., Fraccaro, M., et al.: BIVA: a very deep hierarchy of latent variables for generative modeling. In: NeurIPS (2019)

    Google Scholar 

  18. Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, J.I.: Adversarial autoencoders. CoRR (2015)

    Google Scholar 

  19. Metz, L., Poole, B., et al.: Unrolled generative adversarial networks. In: ICLR (2017)

    Google Scholar 

  20. Van den Oord, A., Kalchbrenner, N., et al.: Conditional image generation with PixelCNN decoders. In: Advances in Neural Information Processing Systems, pp. 4790–4798 (2016)

    Google Scholar 

  21. Rezende, D.J., Mohamed, S., et al.: Stochastic backpropagation and approximate inference in deep generative models. In: ICML (2014)

    Google Scholar 

  22. Salimans, T., Goodfellow, I., et al.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, pp. 2234–2242 (2016)

    Google Scholar 

  23. Salimans, T., Karpathy, A., Chen, X., Kingma, P.D.: PixelCNN++: improving the PixelCNN with discretized logistic mixture likelihood and other modifications. In: ICLR (2017)

    Google Scholar 

  24. Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, pp. 11895–11907 (2019)

    Google Scholar 

  25. Takahashi, H., Iwata, T., et al.: Variational autoencoder with implicit optimal priors. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 5066–5073 (2019)

    Google Scholar 

  26. Tomczak, J., Welling, M.: VAE with a VampPrior. In: International Conference on Artificial Intelligence and Statistics, pp. 1214–1223 (2018)

    Google Scholar 

  27. Tomczak, J.M., Welling, M.: Improving variational auto-encoders using householder flow. arXiv preprint arXiv:1611.09630 (2016)

  28. Wu, J., Huang, Z., Thoma, J., Acharya, D., Van Gool, L.: Wasserstein divergence for GANs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 673–688. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_40

    Chapter  Google Scholar 

  29. Xiao, H., Rasul, K., et al.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms (2017)

    Google Scholar 

Download references

Acknowledgments

This work has been supported by National Key R&D Program of China 2019YFB1802504 and the Beijing National Research Center for Information Science and Technology (BNRist) key projects.

Author information

Authors and Affiliations

  1. Department of Computer Science and Technology, Tsinghua University, Beijing, China

    Wenxiao Chen, Wenda Liu, Zhenting Cai, Haowen Xu & Dan Pei

  2. Beijing National Research Center for Information Science and Technology (BNRist), Beijing, China

    Wenxiao Chen, Haowen Xu & Dan Pei

Authors
  1. Wenxiao Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wenda Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhenting Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Haowen Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Dan Pei
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dan Pei .

Editor information

Editors and Affiliations

  1. Department of AI, Ping An Life, Shenzhen, China

    Haiqin Yang

  2. Faculty of Information Technology, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand

    Kitsuchart Pasupa

  3. City University of Hong Kong, Kowloon, Hong Kong

    Andrew Chi-Sing Leung

  4. Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, Hong Kong

    James T. Kwok

  5. School of Information Technology, King Mongkut’s University of Technology Thonburi, Bangkok, Thailand

    Jonathan H. Chan

  6. The Chinese University of Hong Kong, New Territories, Hong Kong

    Irwin King

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chen, W., Liu, W., Cai, Z., Xu, H., Pei, D. (2020). VAEPP: Variational Autoencoder with a Pull-Back Prior. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science(), vol 12534. Springer, Cham. https://doi.org/10.1007/978-3-030-63836-8_31

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-63836-8_31

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-63835-1

  • Online ISBN: 978-3-030-63836-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation