Abstract
Recently, a new feature representation method called deep canonical correlation analysis (DCCA) has been proposed with high learning performance for multiview feature extraction of high dimensional data. DCCA is an effective approach to learn the nonlinear mappings of two sets of random variables that make the resulting DNN representations highly correlated. However, the DCCA learning process is unsupervised and thus lacks the class label information of training samples on the two views. In order to take full advantage of the class information of training samples, we propose a discriminative version of DCCA referred to as supervised DCCA (SDCCA) for feature learning, which explicitly considers the class information of samples. Compared with DCCA, the SDCCA method can not only guarantee the nonlinear maximal correlation between two views, but also minimize within-class scatter of the samples. With supervision, SDCCA can extract more discriminative features for pattern classification tasks. We test SDCCA on the handwriting recognition and speech recognition using two popular MNIST and XRMB datasets. Experimental results show that SDCCA gets higher performance than several related algorithms.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Here DNNs f and g are regarded as two nonlinear mappings. Thus, f(X) and g(Y) denote the DNN outputs (top-level representations) on the two views.
- 2.
- 3.
References
Hotelling, H.: Relations between two sets of variates. Biometrika 28(3/4), 321–377 (1936)
Sun, Q.S., Liu, Z.-D., Heng, P.-A., Xia, D.-S.: A theorem on the generalized canonical projective vectors. Pattern Recogn. 38(3), 449–452 (2005)
Lai, P.L., Fyfe, C.: Kernel and nonlinear canonical correlation analysis. Int. J. Neural Syst. 10(5), 365 (2000)
Andrew, G., Arora, R., Bilmes, J., Livescu, K.: Deep canonical correlation analysis. In: ICML, pp. III-1247–III-1255. JMLR: W&CP, Atlanta (2013)
Yan, F., Mikolajczyk, K.: Deep correlation for matching images and text. In: CVPR, pp. 3441–3451. IEEE, Boston (2015)
Wang, W., Yan, X., Lee, H., Livescu, K.: Deep variational canonical correlation analysis arXiv preprint arXiv:1610.03454v3 (2017)
Wang, W., Arora, R., Livescu, K., Bilmes, J.: On deep multi-view representation learning. In: ICML, pp. 1083–1092. JMLR: W&CP, Lille (2015)
Melzer, T., Reiter, M., Bischof, H.: Appearance models based on kernel canonical correlation analysis. Pattern Recogn. 36(9), 1961–1971 (2003)
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.-A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371–3408 (2010)
Michaeli, T., Wang, W., Livescu, K.: Nonparametric canonical correlation analysis. In: ICML, pp. 1967–1976. JMLR: W&CP, New York (2016)
Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. ACM TIST 2(3) (2011). Article No. 27
Wang, W., Arora, R., Livescu, K., Bilmes, J.: Unsupervised learning of acoustic features via deep canonical correlation analysis. In: ICASSP, pp. 4590–4594. IEEE, Brisbane (2015)
Acknowledgements
This work is supported by National Natural Science Foundation of China under Grant No. 61402203. In addition, it is also supported in part by the National Natural Science Foundation of China under Grant Nos. 61472344, 61611540347, the Natural Science Foundation of Jiangsu Province of China under Grant Nos. BK20161338, BK20170513, and sponsored by Excellent Young Backbone Teacher Project.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Liu, Y., Li, Y., Yuan, YH., Qiang, JP., Ruan, M., Zhang, Z. (2017). Supervised Deep Canonical Correlation Analysis for Multiview Feature Learning. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10639. Springer, Cham. https://doi.org/10.1007/978-3-319-70136-3_61
Download citation
DOI: https://doi.org/10.1007/978-3-319-70136-3_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70135-6
Online ISBN: 978-3-319-70136-3
eBook Packages: Computer ScienceComputer Science (R0)