Abstract
Canonical Correlation Analysis (CCA) is the root method in the area of multi-view representation learning, but this method does not utilize the class information of the samples. Discriminative Canonical Correlation Analysis (DCCA) is developed based on CCA which takes the class information into consideration. However, DCCA is unable to take advantages of numerous unsupervised data and may perform poorly in real-world problems. Thus, we propose a method called Manifold Regularized Discriminative Canonical Correlation Analysis for Semi-supervised Data (MRDCCA). Our algorithm can not only use labeled samples to preserve the discriminant structure, but also estimate the intrinsic geometric manifold structure of data with both labeled and unlabeled samples by introducing the Laplacian regularization terms. Experimental results on Multiple Features database and face databases show the proposed approach can provide a better recognition performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li Y, Yang M, Zhang Z (2016) Multi-view representation learning: a survey from shallow methods to deep methods
Liu W, Tao D, Cheng J, Tang Y (2014) Multiview hessian discriminative sparse coding for image annotation. Comput Vis Image Underst 118(1):50–60
Srivastava N, Salakhutdinov R (2014) Multimodal learning with deep boltzmann machines. J Mach Learn Res 15(8):1967–2006
Zhou XD, Chen XH, Chen SC (2012) Combined-feature-discriminability enhanced canonical correlation analysis. Pattern Recog Artif Intell 25(2):285–291
Sun T, Chen S, Yang J, Shi P (2008) A novel method of combined feature extraction for recognition. In: Eighth IEEE international conference on data mining. IEEE Computer Society, pp 1043–1048
Zhu X (2005) Semi-supervised learning literature survey. Computer. Science 37(1):63–77
Zhu X, Ghahramani Z, Lafferty J (2003) Semi-supervised learning using Gaussian fields and harmonic functions. In: Twentieth international conference on international conference on machine learning. AAAI Press, pp 912–919
Belkin M, Niyogi P, Sindhwani V (2004) Manifold regularization: a geometric framework for learning from examples. J Mach Learn Res 7(1):2399–2434
Cai D, He X, Han J (2007) Semi-supervised discriminant analysis. In: IEEE, international conference on computer vision. IEEE, pp 1–7
Lu XL (2015) Research of face recognition algorithm based on semi-supervised learning method. University of Electronic Science and Technology, Chengdu (in Chinese)
Kong YQ (2009) Studies on semi-supervised learning and its applications. Jiangnan University, Wuxi (in Chinese)
Feng W, Xie L, Zeng J, Liu ZQ (2009) Audio-visual human recognition using semi-supervised spectral learning and hidden markov models. J Vis Lang Comput 20(3):188–195
Blaschko MB, Lampert CH, Gretton A (2008) Semi-supervised Laplacian regularization of Kernel canonical correlation analysis. In: European conference on machine learning and knowledge discovery in databases. Springer, Berlin, pp 133–145
Yin M, Gao J, Lin Z (2016) Laplacian regularized low-rank representation and its applications. IEEE Trans Pattern Anal Mach Intell 38(3):504–517
Peng Y (2008) Locality discriminative canonical correlation analysis algorithm. Comput Eng Appl 44(21):126–129
Sun TK (2006) Research on enhanced canonical correlation analysis with applications. University of Aeronautics & Astronautics, Nanjing (in Chinese)
Acknowledgements
This project is supported by National Natural Science Foundation of China (Grant No. 6161154034).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wu, H., Zhou, X. (2018). Manifold Regularized Discriminative Canonical Correlation Analysis for Semi-supervised Data. In: Deng, Z. (eds) Proceedings of 2017 Chinese Intelligent Automation Conference. CIAC 2017. Lecture Notes in Electrical Engineering, vol 458. Springer, Singapore. https://doi.org/10.1007/978-981-10-6445-6_19
Download citation
DOI: https://doi.org/10.1007/978-981-10-6445-6_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6444-9
Online ISBN: 978-981-10-6445-6
eBook Packages: EngineeringEngineering (R0)