Canonical Correlation Analysis for Multiview Semisupervised Feature Extraction

  • Olcay Kursun
  • Ethem Alpaydin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6113)


Hotelling’s Canonical Correlation Analysis (CCA) works with two sets of related variables, also called views, and its goal is to find their linear projections with maximal mutual correlation. CCA is most suitable for unsupervised feature extraction when given two views but it has been also long known that in supervised learning when there is only a single view of data given, the supervision signal (class-labels) can be given to CCA as the second view and CCA simply reduces to Fisher’s Linear Discriminant Analysis (LDA). However, it is unclear how to use this equivalence for extracting features from multiview data in semisupervised setting (i.e. what modification to the CCA mechanism could incorporate the class-labels along with the two views of the data when labels of some samples are unknown). In this paper, a CCA-based method supplemented by the essence of LDA is proposed for semi-supervised feature extraction from multiview data.


Semisupervised Learning Feature Extraction Multiview Learning LDA CCA 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fisher, R.A.: The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics 7, 179–188 (1936)Google Scholar
  2. 2.
    Hotelling, H.: Relations between two sets of variates. Biometrika 28, 321–377 (1936)MATHGoogle Scholar
  3. 3.
    Favorov, O.V., Ryder, D.: SINBAD: a neocortical mechanism for discovering environmental variables and regularities hidden in sensory input. Biological Cybernetics 90, 191–202 (2004)MATHCrossRefGoogle Scholar
  4. 4.
    Kettenring, J.R.: Canonical analysis of several sets of variables. Biometrika 58, 433–451 (1971)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Bartlett, M.S.: Further aspects of the theory of multiple regression. Proc. Camb. Philos. Soc. 34, 33–40 (1938)CrossRefGoogle Scholar
  6. 6.
    Hardoon, D., Szedmak, S., Shawe-Taylor, J.: Canonical correlation analysis: an overview with application to learning methods. Neural Computation 16, 2639–2664 (2004)MATHCrossRefGoogle Scholar
  7. 7.
    Alpaydin, E.: Introduction to Machine Learning (Adaptive Computation and Machine Learning Series). The MIT Press, Cambridge (2004)Google Scholar
  8. 8.
    Loog, M., van Ginneken, B., Duin, R.P.W.: Dimensionality reduction of image features using the canonical contextual correlation projection. Pattern Recognition 38, 2409–2418 (2005)CrossRefGoogle Scholar
  9. 9.
    Barker, M., Rayens, W.: Partial least squares for discrimination. Journal of Chemometrics 17, 166–173 (2003)CrossRefGoogle Scholar
  10. 10.
    Sun, T., Chen, S.: Class label versus sample label-based CCA. Applied Mathematics and Computation 185, 272–283 (2007)MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    van Breukelen, M., Duin, R.P.W., Tax, D.M.J., den Hartog, J.E.: Handwritten digit recognition by combined classifiers. Kybernetika 34(4), 381–386 (1998)Google Scholar
  12. 12.
    Asuncion, A., Newman, D.J.: UCI Machine Learning Repository. University of California, Department of Information and Computer Science, Irvine (2007)Google Scholar
  13. 13.
    Borga, M.: Learning Multidimensional signal processing, PhD thesis, Department of Electrical Engineering, Linköping University, Linköping, Sweden (1998)Google Scholar
  14. 14.
    Hsu, C.W., Lin, C.J.: A Comparison of Methods for Multi-Class Support Vector Machines. IEEE Trans. Neural Networks 13, 415–425 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Olcay Kursun
    • 1
  • Ethem Alpaydin
    • 2
  1. 1.Department of Computer EngineeringIstanbul UniversityAvcilarTurkey
  2. 2.Department of Computer EngineeringBogazici UniversityBebekTurkey

Personalised recommendations