Auto-encoder Based Co-training Multi-view Representation Learning

  • Run-kun Lu
  • Jian-wei LiuEmail author
  • Yuan-fang Wang
  • Hao-jie Xie
  • Xin Zuo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11441)


Multi-view learning is a learning problem that utilizes the various representations of an object to mine valuable knowledge and improve the performance of learning algorithm, and one of the significant directions of multi-view learning is sub-space learning. As we known, auto-encoder is a method of deep learning, which can learn the latent feature of raw data by reconstructing the input, and based on this, we propose a novel algorithm called Auto-encoder based Co-training Multi-View Learning (ACMVL), which utilizes both complementarity and consistency and finds a joint latent feature representation of multiple views. The algorithm has two stages, the first is to train auto-encoder of each view, and the second stage is to train a supervised network. Interestingly, the two stages share the weights partly and assist each other by co-training process. According to the experimental result, we can learn a well performed latent feature representation, and auto-encoder of each view has more powerful reconstruction ability than traditional auto-encoder.


Multi-view Auto-encoder Co-training 


  1. 1.
    Bickel, S., Scheffer, T.: Multi-view clustering. In: Proceedings of the 4th IEEE International Conference on Data Mining (ICDM 2004), Brighton, UK, 1–4 November 2004, pp. 19–26 (2004)Google Scholar
  2. 2.
    Blum, A., Mitchell, T.M.: Combining labeled and unlabeled data with co-training. In: Proceedings of the Eleventh Annual Conference on Computational Learning Theory, COLT 1998, Madison, Wisconsin, USA, 24–26 July 1998, pp. 92–100 (1998)Google Scholar
  3. 3.
    Brefeld, U., Büscher, C., Scheffer, T.: Multi-view discriminative sequential learning. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol. 3720, pp. 60–71. Springer, Heidelberg (2005). Scholar
  4. 4.
    Brefeld, U., Scheffer, T.: Co-EM support vector learning. In: Proceedings of the Twenty-First International Conference on Machine Learning, (ICML 2004), Banff, Alberta, Canada, 4–8 July 2004 (2004)Google Scholar
  5. 5.
    Chaudhuri, K., Kakade, S.M., Livescu, K., Sridharan, K.: Multi-view clustering via canonical correlation analysis. In: Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, Montreal, Quebec, Canada, 14–18 June 2009, pp. 129–136 (2009)Google Scholar
  6. 6.
    Chen, M., Weinberger, K.Q., Chen, Y.: Automatic feature decomposition for single view co-training. In: Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, USA, 28 June–2 July 2011, pp. 953–960 (2011)Google Scholar
  7. 7.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2010, Chia Laguna Resort, Sardinia, Italy, 13–15 May 2010, pp. 249–256 (2010)Google Scholar
  8. 8.
    Jin, X., Zhuang, F., Wang, S., He, Q., Shi, Z.: Shared structure learning for multiple tasks with multiple views. In: Blockeel, H., Kersting, K., Nijssen, S., Železný, F. (eds.) ECML PKDD 2013. LNCS (LNAI), vol. 8189, pp. 353–368. Springer, Heidelberg (2013). Scholar
  9. 9.
    Kingma, D.P., Welling, M.: Auto-encoding variational bayes. CoRR abs/1312.6114 (2013)Google Scholar
  10. 10.
    Kursun, O., Alpaydin, E.: Canonical correlation analysis for multiview semisupervised feature extraction. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010. LNCS (LNAI), vol. 6113, pp. 430–436. Springer, Heidelberg (2010). Scholar
  11. 11.
    Liu, J., Jiang, Y., Li, Z., Zhou, Z., Lu, H.: Partially shared latent factor learning with multiview data. IEEE Trans. Neural Netw. Learn. Syst. 26(6), 1233–1246 (2015)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Ou, W., Long, F., Tan, Y., Yu, S., Wang, P.: Co-regularized multiview nonnegative matrix factorization with correlation constraint for representation learning. Multimed. Tools Appl. 77(10), 12955–12978 (2018)CrossRefGoogle Scholar
  13. 13.
    Wang, Z., Chen, S., Gao, D.: A novel multi-view learning developed from single-view patterns. Pattern Recogn. 44(10–11), 2395–2413 (2011)CrossRefGoogle Scholar
  14. 14.
    Xu, C., Tao, D., Xu, C.: A survey on multi-view learning. CoRR abs/1304.5634 (2013)Google Scholar
  15. 15.
    Zeiler, M.D.: ADADELTA: an adaptive learning rate method. CoRR abs/1212.5701 (2012)Google Scholar
  16. 16.
    Zhang, Z., Qin, Z., Li, P., Yang, Q., Shao, J.: Multi-view discriminative learning via joint non-negative matrix factorization. In: Pei, J., Manolopoulos, Y., Sadiq, S., Li, J. (eds.) DASFAA 2018. LNCS, vol. 10828, pp. 542–557. Springer, Cham (2018). Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Run-kun Lu
    • 1
  • Jian-wei Liu
    • 1
    Email author
  • Yuan-fang Wang
    • 1
  • Hao-jie Xie
    • 1
  • Xin Zuo
    • 1
  1. 1.Department of AutomationChina University of PetroleumBeijingChina

Personalised recommendations