Skip to main content
SpringerLink
Log in

Robust and smart spectral clustering from normalized cut

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

How to determine the scale parameter and the cluster number are two important open issues of spectral clustering remained to be studied. In this paper, it is aimed to overcome these two problems. Firstly, we analyze the principle of spectral clustering from normalized cut. Secondly, on one hand, a weighted local scale was proposed to improve both the classification performance and robustness. On the other hand, we proposed an automatic cluster number estimation method from standpoint of Eigenvectors of its affinity matrix. Finally, a framework of robust and smart spectral clustering method was concluded; it is robust enough to deal with arbitrary distributed datasets and smart enough to estimate cluster number automatically. The proposed method was tested both on artificial datasets and UCI datasets, and experiments prove its availability.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv 31(3):264–323

    Article  Google Scholar 

  2. Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley, New York

    Google Scholar 

  3. Luxburg U (2007) A tutorial on spectral clustering. Stat Comput 17(4):395–416

    Article  MathSciNet  Google Scholar 

  4. Filipponea M, Camastrab F, Masullia F, Rovetta S (2008) A survey of kernel and spectral methods for clustering. Pattern Recognit 41(1):176–190

    Article  Google Scholar 

  5. Nga Y, Jordan MI, Weiss Y(2002) On spectral clustering: analysis and an algorithm. Proceedings of the 14th advances in neural information processing systems (NIPS). MIT Press, Cambridge, vol. 200, pp 849–856

  6. Nascimento MCV, de Carvalho ACPLF (2011) Spectral methods for graph clustering—a survey. Eur J Oper Res 211:221–231

    Article  MATH  Google Scholar 

  7. Chen W, Feng G (2012) Spectral clustering: a semi-supervised approach. Neurocomputing 77:229–242

    Article  Google Scholar 

  8. Ozertem U, Erdogmus D, Jenssen R (2008) Mean shift spectral clustering. Pattern Recognit 41:1924–1938

    Article  MATH  Google Scholar 

  9. Yang P, Zhu Q, Huang B (2011) Spectral clustering with density sensitive similarity function. Knowl Based Syst 24(5):621–628

    Article  Google Scholar 

  10. Chang H, Yeung DH (2008) Robust path-based spectral clustering. Pattern Recognit 41(1):191–203

    Article  MathSciNet  MATH  Google Scholar 

  11. Lihi ZM, Pietro P (2005) Self-tuning spectral clustering. Adv Neural Inform Process Syst 17:1601–1608

    Google Scholar 

  12. Zhang X, Li J, Yu H (2011) Local density adaptive similarity measurement for spectral clustering. Pattern Recognit Lett 32(2):352–358

    Article  Google Scholar 

  13. Kong W, Sun Z, Yang C et al (2010) Automatic spectral clustering based on eigengap and orthogonal eigenvector. Acta Electronica Sinica 38(8):1980–1985

    Google Scholar 

  14. Rebagliati N, Verri A (2011) Spectral clustering with more than K eigenvectors. Neurocomputing 74:1391–1401

    Article  Google Scholar 

  15. Wu Z, Leahy R (1993) An optimal graph theoretic approach to data clustering: theory and its application to image segmentation. IEEE Trans Pattern Anal Mach Intell 15(11):1101–1113

    Article  Google Scholar 

  16. Meila M, Xu L (2004) Multiway cuts and spectral clustering. Technical Report, Department of Statistics, University of Washington, Washington

  17. Yu SX, Shi J (2004) Segmentation given partial grouping constraints. IEEE Trans Pattern Anal Mach Intell 26(2):173–183

    Article  Google Scholar 

  18. Hagen L, Kahng AB (1992) New spectral methods for ratio cut partitioning and clustering. IEEE Trans Comput Aided Des 11(9):1074–1085

    Article  Google Scholar 

  19. Ding C, He X, Zha H, Gu M, Simon H (2001) A min–max cut algorithm for graph partitioning and data clustering. In: Proceedings of the IEEE international conference on data mining, pp 107–114

  20. Chen W, Feng G (2012) Spectral clustering with discriminant cuts. Knowl Based Syst 28:27–37

    Article  Google Scholar 

  21. Dhillon IS, Guan Y, Kulis B (2004) Kernel k-means: spectral clustering and normalized cuts. In: International Conference on KDD, pp 551–556

Download references

Acknowledgments

The work was supported by National Natural Science Foundation of China (No. 61102028 and No. 61070127), and International Cooperation Project of Zhejiang Province, China (No. 2009C14013 and No.2011C14017).

Author information

Authors and Affiliations

  1. College of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, People’s Republic of China

    Wanzeng Kong, Sanqing Hu, Jianhai Zhang & Guojun Dai

Authors
  1. Wanzeng Kong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sanqing Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jianhai Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guojun Dai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wanzeng Kong.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kong, W., Hu, S., Zhang, J. et al. Robust and smart spectral clustering from normalized cut. Neural Comput & Applic 23, 1503–1512 (2013). https://doi.org/10.1007/s00521-012-1101-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-012-1101-4

Keywords

Search

Navigation