Advertisement

A Binary Variational Autoencoder for Hashing

  • Francisco MenaEmail author
  • Ricardo ÑanculefEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11896)

Abstract

Searching a large dataset to find elements that are similar to a sample object is a fundamental problem in computer science. Hashing algorithms deal with this problem by representing data with similarity-preserving binary codes that can be used as indices into a hash table. Recently, it has been shown that variational autoencoders (VAEs) can be successfully trained to learn such codes in unsupervised and semi-supervised scenarios. In this paper, we show that a variational autoencoder with binary latent variables leads to a more natural and effective hashing algorithm that its continuous counterpart. The model reduces the quantization error introduced by continuous formulations but is still trainable with standard back-propagation. Experiments on text retrieval tasks illustrate the advantages of our model with respect to previous art.

Keywords

Hashing Variational autoencoders Deep learning Gumbel-Softmax distribution Neural information retrieval 

Notes

Acknowledgement

F. Mena thanks the Programa de Iniciación Científica PIIC-DGIP of the Federico Santa María University for funding this work.

References

  1. 1.
    Baeza-Yates, R., Ribeiro-Neto, B.: Modern Information Retrieval. ACM Press, New York (1999)Google Scholar
  2. 2.
    Carreira-Perpinán, M.A., Raziperchikolaei, R.: Hashing with binary autoencoders. In: Proceedings of the CVPR, pp. 557–566 (2015)Google Scholar
  3. 3.
    Chaidaroon, S., Fang, Y.: Variational deep semantic hashing for text documents. In: Proceedings of the 40th SIGIR, pp. 75–84. ACM (2017)Google Scholar
  4. 4.
    Do, T.-T., Doan, A.-D., Cheung, N.-M.: Learning to hash with binary deep neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 219–234. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46454-1_14CrossRefGoogle Scholar
  5. 5.
    Gong, Y., Lazebnik, S., Gordo, A., Perronnin, F.: Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2916–2929 (2013)CrossRefGoogle Scholar
  6. 6.
    Jang, E., Gu, S., Poole, B.: Categorical reparameterization with Gumbel-softmax. In: Proceedings of the ICLR (2017)Google Scholar
  7. 7.
    Kingma, D.P., Welling, M.: Auto-encoding variational Bayes (2013)Google Scholar
  8. 8.
    Kulis, B., Grauman, K.: Kernelized locality-sensitive hashing. IEEE Trans. Pattern Anal. Mach. Intell. 34(6), 1092–1104 (2012)CrossRefGoogle Scholar
  9. 9.
    Liong, V.E., Lu, J., Wang, G., Moulin, P., Zhou, J.: Deep hashing for compact binary codes learning. In: Proceedings of the CVPR, vol. 2015, pp. 2475–2483 (2015)Google Scholar
  10. 10.
    Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: a continuous relaxation of discrete random variables. arXiv preprint arXiv:1611.00712 (2016)
  11. 11.
    Norouzi, M., Punjani, A., Fleet, D.J.: Fast exact search in hamming space with multi-index hashing. IEEE PAMI 36(6), 1107–1119 (2014)CrossRefGoogle Scholar
  12. 12.
    Salakhutdinov, R., Hinton, G.: Semantic hashing. Int. J. Approximate Reasoning 50(7), 969–978 (2009)CrossRefGoogle Scholar
  13. 13.
    Silveira, D., Carvalho, A., Cristo, M., Moens, M.F.: Topic modeling using variational auto-encoders with Gumbel-softmax and logistic-normal mixture distributions. In: International Joint Conference on Neural Networks (IJCNN). IEEE (2018)Google Scholar
  14. 14.
    Wang, J., Kumar, S., Chang, S.F.: Semi-supervised hashing for large-scale search. IEEE Trans. Pattern Anal. Mach. Intell. 34(12), 2393–2406 (2012)CrossRefGoogle Scholar
  15. 15.
    Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: NIPS (2009)Google Scholar
  16. 16.
    Xu, J., et al.: Convolutional neural networks for text hashing. In: Proceedings of the IJCAI 2015 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Federico Santa María UniversitySantiagoChile

Personalised recommendations