We propose a novel approach to clustering, based on deterministic analysis of random walks on the weighted graph associated with the clustering problem. The method is centered around what we shall call separating operators, which are applied repeatedly to sharpen the distinction between the weights of inter-cluster edges (the so-called separators), and those of intra-cluster edges. These operators can be used as a stand-alone for some problems, but become particularly powerful when embedded in a classical multi-scale framework and/or enhanced by other known techniques, such as agglomerative clustering. The resulting algorithms are simple, fast and general, and appear to have many useful applications.


Random Walk Edge Weight Weighted Graph Separation Operator Agglomerative Cluster 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    V. Estivill-Castro and I. Lee,“AUTOCLUST: Automatic Clustering via Boundary Extraction for Mining Massive Point-Data Sets”, 5th International Conference on Geocomputation, GeoComputation CD-ROM: GC049, ISBN 0-9533477-2-9.Google Scholar
  2. 2.
    Y. Gdalyahu, D. Weinshall and M. Werman, “Stochastic Image Segmentation by Typical Cuts”, Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 1999, pp. 588–601.Google Scholar
  3. 3.
    S. Guha, R. Rastogi and K. Shim, “ROCK: A Robust Clustering Algorithm for Categorical Attributes”, Proceedings of the 15th International Conference on Data Engineering, pp. 512–521, 1999.Google Scholar
  4. 4.
    L. Hagen and A. Kahng, “A New Approach to Effective Circuit Clustering”, Proceedings of the IEEE/ACM International Conference on Computer-Aided Design, pp. 422–427, 1992.Google Scholar
  5. 5.
    D. Harel and Y. Koren, “Clustering Spatial Data using Random Walks”, Proc.7th ACM SIGKDD Int.Conf.on Knowledge Discovery and Data Mining (KDD-2001), ACM, pp. 281–286, 2000.Google Scholar
  6. 6.
    D. Harel and Y. Koren, “Clustering Spatial Data Using Random Walks”, Technical Report MCS01-08, Dept. of Computer Science and Applied Mathematics, The Weizmann Institute of Science, 2001. Available at:
  7. 7.
    A. K. Jain and R. C. Dubes, Algorithms for Clustering Data, Prentice Hall, Englewood Cliffs, New Jersy, 1988.zbMATHGoogle Scholar
  8. 8.
    A. K. Jain, M.N. Murty and P.J. Flynn, “Data Clustering: A Review”, ACM Computing Surveys, 31 (1999), 264–323.CrossRefGoogle Scholar
  9. 9.
    G. Karypis, E. Han, and V. Kumar, “CHAMELEON: A Hierarchical Clustering Algorithm Using Dynamic Modeling”, IEEE Computer, 32 (1999), 68–75.Google Scholar
  10. 10.
    G. Karypis and V. Kumar, “A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs”, SIAM Journal on Scientific Computing 20:1 (1999), 359–392.zbMATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    E. Sharon, A. Brandt and R. Basri, “Fast Multiscale Image Segmentation”, Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 70–77, 2000.Google Scholar
  12. 12.
    B. Stein and O. Niggemann, “On the Nature of Structure and its Identification”, Proceedings 25th Workshop on Graph-Theoretic Concepts in Computer Science, LNCS 1665, pp. 122–134, Springer Verlag, 1999.Google Scholar
  13. 13.
    N. Tishby and N. Slonim, “Data Clustering by Markovian relaxation and the Information Bottleneck Method”, Advances in Neural Information Processing Systems 13, 2000.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • David Harel
    • 1
  • Yehuda Koren
    • 1
  1. 1.Dept. of Computer Science and Applied MathematicsThe Weizmann Institute of ScienceRehovotIsrael

Personalised recommendations