Encyclopedia of Machine Learning

2010 Edition
| Editors: Claude Sammut, Geoffrey I. Webb

Projective Clustering

  • Cecilia M. Procopiuc
Reference work entry
DOI: https://doi.org/10.1007/978-0-387-30164-8_676

Synonyms

Definition

Projective clustering is a class of problems in which the input consists of high-dimensional data, and the goal is to discover those subsets of the input that are strongly correlated in subspaces of the original space. Each subset of correlated points, together with its associated subspace, defines a projective cluster. Thus, although all cluster points are close to each other when projected on the associated subspace, they may be spread out in the full-dimensional space. This makes projective clustering algorithms particularly useful when mining or indexing datasets for which full-dimensional clustering is inadequate (as is the case for most high-dimensional inputs). Moreover, such algorithms compute projective clusters that exist in different subspaces, making them more general than global dimensionality-reduction techniques.

Motivation and Background

Projective clustering is a type of data mining whose main...
This is a preview of subscription content, log in to check access

Recommended Reading

  1. Agarwal, P. K., Har-Peled, S., & Varadarajan, K. R. (2005). Geometric approximation via coresets. Combinatorial and Computational Geometry (pp. 1–30).Google Scholar
  2. Agarwal, P. K., & Mustafa, N. (2004). k-means projective clustering. In Proceeding of ACM SIGMOD-SIGACT-SIGART symposium principles of database systems (pp. 155–165).Google Scholar
  3. Agarwal, P. K., & Procopiuc, C. M. (2003). Approximation algorithms for projective clustering. Journal of Algorithms, 46(2), 115–139.MathSciNetMATHCrossRefGoogle Scholar
  4. Agrawal, R., Gehrke, J., Gunopulos, D., & Raghavan, P. (1998). Automatic subspace clustering of high dimensional data for data mining applications. In Proceeding of ACM SIGMOD international conference management of data (pp. 94–105).Google Scholar
  5. Aggarwal, C. C., Procopiuc, C. M., Wolf, J. L., Yu, P. S., & Park, J. S. (1999). Fast algorithms for projected clustering. In Proceeding of ACM SIGMOD international conference management of data (pp. 61–72).Google Scholar
  6. Aggarwal, C. C., & Yu, P. S. (2000). Finding generalized projected clusters in high dimensional spaces. In Proceeding of ACM SIGMOD international conference management of data (pp. 70–81).Google Scholar
  7. Beyer, K., Goldstein, J., Ramakrishnan, R., & Shaft, U. (1999). When is “nearest neighbour” meaningful? In Proceeding of 7th international conference data theory (Vol. 1540, pp. 217–235).Google Scholar
  8. Böhm, C., Kailing, K., Kröger, P., & Zimek, A. (2004). Computing clusters of correlation connected objects. In Proceeding of ACM SIGMOD international conference management of data (pp. 455–466).Google Scholar
  9. Chakrabarti, K., & Mehrotra, S. (2000). Local dimensionality reduction: A new approach to indexing high dimensional spaces. In Proceeding of 26th international conference very large data bases (pp. 89–100).Google Scholar
  10. Hinneburg, A., & Keim, D. A. (1999). Optimal grid-clustering: Towards breaking the curse of dimensionality in high-dimensional clustering. In Proceeding of 25th international conference very large data bases (pp. 506–517).Google Scholar
  11. Li, T., Ma, S., & Ogihara, M. (2004). Document clustering via adaptive subspace iteration. In Proceeding of 27th international ACM SIGIR conference research and development in information retrieval (pp. 218–225).Google Scholar
  12. Liu, J., & Wang, W. (2003). Op-cluster: Clustering by tendency in high dimensional space. In Proceeding of international conference on data mining (pp. 187–194).Google Scholar
  13. Megiddo, N., & Tamir, A. (1982). On the complexity of locating linear facilities in the plane. Operations Research Letters, 1, 194–197.MathSciNetMATHCrossRefGoogle Scholar
  14. Parsons, L., Haque, E., & Liu, H. (2004). Subspace clustering for high dimensional data: A review. ACM SIGKDD Explorations Newsletter, 6(1), 90–105.CrossRefGoogle Scholar
  15. Procopiuc, C. M., Jones, M., Agarwal, P. K., & Murali, T. M. (2002). A monte carlo algorithm for fast projective clustering. In Proceeding of ACM SIGMOD international conference management of data (pp. 418–427).Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Cecilia M. Procopiuc
    • 1
  1. 1.AT&T LabsFlorham ParkUSA