Data Ranking and Clustering via Normalized Graph Cut Based on Asymmetric Affinity

  • Olexiy Kyrgyzov
  • Isabelle Bloch
  • Yuan Yang
  • Joe Wiart
  • Antoine Souloumiac
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8157)


In this paper, we present an extension of the state-of-the-art normalized graph cut method based on asymmetry of the affinity matrix. We provide algorithms for classification and clustering problems and show how our method can improve solutions for unequal and overlapped data distributions. The proposed approaches are based on the theoretical relation between classification accuracy, mutual information and normalized graph cut. The first method requires a priori known class labeled data that can be utilized, e.g., for a calibration phase of a brain-computer interface (BCI). The second one is a hierarchical clustering method that does not involve any prior information on the dataset.


graph cut asymmetric affinity mutual information BCI 


  1. 1.
    Bollobas, B.: Modern graph theory (Graduate Texts in Mathematics), vol. 184. Springer (1998)Google Scholar
  2. 2.
    Forsyth, D., Ponce, J.: Computer Vision: A Modern Approach, 2nd edn. Prentice Hall (October 2011)Google Scholar
  3. 3.
    Golub, G., Loan, C.V.: Matrix Computations. John Hopkins Press (1989)Google Scholar
  4. 4.
    Kyrgyzov, O., Souloumiac, A.: Adaptive EEG artifact rejection for cognitive games. In: 14th ACM International Conference on Multimodal Interaction, ICMI 2012, pp. 567–570 (2012)Google Scholar
  5. 5.
    Lan, T., Erdogmus, D., Adami, A., Pavel, M., Mathan, S.: Salient EEG channel selection in brain computer interfaces by mutual information maximization. In: 27th Annual Conference on Engineering in Medicine and Biology, pp. 7064–7067 (2005)Google Scholar
  6. 6.
    Learned-Miller III, E., Fisher, J.: ICA using spacings estimates of entropy. Journal of Machine Learning Research 4, 1271–1295 (2003)MathSciNetGoogle Scholar
  7. 7.
    Meila, M., Pentney, W.: Clustering by weighted cuts in directed graphs. In: SIAM International Conference on Data Mining, pp. 135–144 (2007)Google Scholar
  8. 8.
    Nascimento, M., de Carvalho, A.: Spectral methods for graph clustering - a survey. European Journal of Operational Research 211(2), 221–231 (2011)CrossRefzbMATHMathSciNetGoogle Scholar
  9. 9.
    Ng, A., Jordan, M., Weiss, Y.: On spectral clustering: Analysis and an algorithm. In: Proc. 14th Advances in Neural Information Processing Systems, pp. 849–856 (2001)Google Scholar
  10. 10.
    Rakotomamonjy, A., Guigue, V.: BCI competition III: Dataset II - ensemble of SVMs for BCI P300 speller. IEEE Transactions on Biomedical Engineering 5(3), 1147–1154 (2008)CrossRefGoogle Scholar
  11. 11.
    Schaeffer, S.: Graph clustering. Computer Science Review 1(1), 27–64 (2007)CrossRefMathSciNetGoogle Scholar
  12. 12.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(8), 888–905 (2000)CrossRefGoogle Scholar
  13. 13.
    Silverman, B.W.: Density Estimation for Statistics and Data Analysis. Chapman & Hall, London (1986)CrossRefzbMATHGoogle Scholar
  14. 14.
    Wu, Z., Leahy, R.: An optimal graph theoretic approach to data clustering: Theory and its application to image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 15(11), 1101–1113 (1993)CrossRefGoogle Scholar
  15. 15.
    Yu, S., Shi, J.: Grouping with directed relationships. In: Figueiredo, M., Zerubia, J., Jain, A.K. (eds.) EMMCVPR 2001. LNCS, vol. 2134, pp. 283–297. Springer, Heidelberg (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Olexiy Kyrgyzov
    • 1
  • Isabelle Bloch
    • 1
  • Yuan Yang
    • 1
  • Joe Wiart
    • 2
  • Antoine Souloumiac
    • 3
  1. 1.Whist LabInstitut Mines-Telecom, ParisTech/CNRS LTCIParisFrance
  2. 2.Whist LabOrange Labs R&DIssy-les-MoulineauxFrance
  3. 3.LIST, Laboratoire Outils Analyse de DonnéesCEAGif-sur-YvetteFrance

Personalised recommendations