Semi-supervised Classification Using Multiple Clustering and Low-Rank Matrix Operations

  • Vladimir BerikovEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11548)


This paper proposes a semi-supervised classification method which combines machine learning regularization framework and cluster ensemble approach. We use the low-rank decomposition of the co-association matrix of the ensemble to significantly speed up calculations and save memory. Numerical experiments using Monte Carlo approach demonstrate the efficiency of the proposed method.


Semi-supervised classification Cluster ensemble Co-association matrix Regularization Low-rank matrix decomposition 



The work was supported by the program of Fundamental Scientific Researches of the RAS, project 0314-2019-0015 of the Sobolev Institute of mathematics. The research was partly supported by RFBR grants 18-07-00600, 18-29-09041mk and partly by the Russian Ministry of Science and Higher Education under Project 5-100. The author thanks anonymous reviewers for helpful comments.


  1. 1.
    Camps-Valls, G., Marsheva, T., Zhou, D.: Semi-supervised graph-based hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 45(10), 3044–3054 (2007)CrossRefGoogle Scholar
  2. 2.
    Zhu, X.: Semi-supervised learning literature survey. Technical report. Department of Computer Science, University of Wisconsin, Madison. N. 1530 (2008)Google Scholar
  3. 3.
    Zhu, X., Ghahramani, Z., Lafferty, J.D.: Semi-supervised learning using Gaussian fields and harmonic functions. In: Proceedings of the 20th International Conference on Machine Learning (ICML 2003), pp. 912–919 (2003)Google Scholar
  4. 4.
    Avrachenkov, K., Mishenin, A., Goncalves, P., Sokol, M.: Generalized optimization framework for graph-based semi-supervised learning. In: Proceedings of the 2012 SIAM International Conference on Data Mining, pp. 966–974 (2012)Google Scholar
  5. 5.
    Boongoen, T., Iam-On, N.: Cluster ensembles: a survey of approaches with recent extensions and applications. Comput. Sci. Rev. 28, 1–25 (2018)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Yu, G.X., Feng, L., Yao, G.J., Wang, J.: Semi-supervised classification using multiple clusterings. Pattern Recognit. Image Anal. 26(4), 681–687 (2016)CrossRefGoogle Scholar
  7. 7.
    Berikov, V., Karaev, N., Tewari, A.: Semi-supervised classification with cluster ensemble. In: 2017 International Multi-Conference Engineering, Computer and Information Sciences (SIBIRCON), pp. 245–250. IEEE (2017)Google Scholar
  8. 8.
    Wu, M., Scholkopf, B.: Transductive classification via local learning regularization. In: Artificial Intelligence and Statistics, pp. 628–635 (2007)Google Scholar
  9. 9.
    Zhou, D., Bousquet, O., Lal, T., Weston, J., Scholkopf, B.: Learning with local and global consistency. In: Advances in Neural Information Processing Systems, pp. 321–328 (2003)Google Scholar
  10. 10.
    Belkin, M., Niyogi, P., Sindhwani, V.: Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J. Mach. Learn. Res. 7, 2399–2434 (2006)MathSciNetzbMATHGoogle Scholar
  11. 11.
    Tikhonov, A.N., Goncharsky, A., Stepanov, V.V., Yagola, A.G.: Numerical Methods for the Solution of Ill-posed Problems. Springer, Dordrecht (2013). Scholar
  12. 12.
    Fred, A., Jain, A.: Combining multiple clusterings using evidence accumulation. IEEE Trans. Pattern Anal. Mach. Intell. 27(6), 835–850 (2005)CrossRefGoogle Scholar
  13. 13.
    Berikov, V.B.: Construction of an optimal collective decision in cluster analysis on the basis of an averaged co-association matrix and cluster validity indices. Pattern Recognit. Image Anal. 27(2), 153–165 (2017)CrossRefGoogle Scholar
  14. 14.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Sobolev Institute of MathematicsNovosibirskRussia
  2. 2.Novosibirsk State UniversityNovosibirskRussia

Personalised recommendations