CLICKS

Mining subspace clusters in categorical data via K-partite maximal cliques

Mohammed J. Zaki, Markus Peters

Research output: Chapter in Book/Report/Conference proceedingConference contribution

33 Citations (Scopus)

Abstract

We present a novel algorithm called CLICKS, that finds clusters in categorical datasets based on a search for k-partite maximal cliques. Unlike previous methods, CLICKS mines subspace clusters. It uses a selective vertical method to guarantee complete search. CLICKS outperforms previous approaches by over an order of magnitude and scales better than any of the existing method for high-dimensional datasets. We demonstrate this improvement in an excerpt from our comprehensive performance studies.

Original languageEnglish
Title of host publicationProceedings - International Conference on Data Engineering
Pages355-356
Number of pages2
DOIs
Publication statusPublished - 12 Dec 2005
Externally publishedYes
Event21st International Conference on Data Engineering, ICDE 2005 - Tokyo, Japan
Duration: 5 Apr 20058 Apr 2005

Other

Other21st International Conference on Data Engineering, ICDE 2005
CountryJapan
CityTokyo
Period5/4/058/4/05

ASJC Scopus subject areas

  • Software
  • Engineering(all)
  • Engineering (miscellaneous)

Cite this

Zaki, M. J., & Peters, M. (2005). CLICKS: Mining subspace clusters in categorical data via K-partite maximal cliques. In Proceedings - International Conference on Data Engineering (pp. 355-356) https://doi.org/10.1109/ICDE.2005.33

CLICKS : Mining subspace clusters in categorical data via K-partite maximal cliques. / Zaki, Mohammed J.; Peters, Markus.

Proceedings - International Conference on Data Engineering. 2005. p. 355-356.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zaki, MJ & Peters, M 2005, CLICKS: Mining subspace clusters in categorical data via K-partite maximal cliques. in Proceedings - International Conference on Data Engineering. pp. 355-356, 21st International Conference on Data Engineering, ICDE 2005, Tokyo, Japan, 5/4/05. https://doi.org/10.1109/ICDE.2005.33
Zaki MJ, Peters M. CLICKS: Mining subspace clusters in categorical data via K-partite maximal cliques. In Proceedings - International Conference on Data Engineering. 2005. p. 355-356 https://doi.org/10.1109/ICDE.2005.33
Zaki, Mohammed J. ; Peters, Markus. / CLICKS : Mining subspace clusters in categorical data via K-partite maximal cliques. Proceedings - International Conference on Data Engineering. 2005. pp. 355-356
@inproceedings{757b71ffb82a491b84a1d54631d4755d,
title = "CLICKS: Mining subspace clusters in categorical data via K-partite maximal cliques",
abstract = "We present a novel algorithm called CLICKS, that finds clusters in categorical datasets based on a search for k-partite maximal cliques. Unlike previous methods, CLICKS mines subspace clusters. It uses a selective vertical method to guarantee complete search. CLICKS outperforms previous approaches by over an order of magnitude and scales better than any of the existing method for high-dimensional datasets. We demonstrate this improvement in an excerpt from our comprehensive performance studies.",
author = "Zaki, {Mohammed J.} and Markus Peters",
year = "2005",
month = "12",
day = "12",
doi = "10.1109/ICDE.2005.33",
language = "English",
isbn = "0769522858",
pages = "355--356",
booktitle = "Proceedings - International Conference on Data Engineering",

}

TY - GEN

T1 - CLICKS

T2 - Mining subspace clusters in categorical data via K-partite maximal cliques

AU - Zaki, Mohammed J.

AU - Peters, Markus

PY - 2005/12/12

Y1 - 2005/12/12

N2 - We present a novel algorithm called CLICKS, that finds clusters in categorical datasets based on a search for k-partite maximal cliques. Unlike previous methods, CLICKS mines subspace clusters. It uses a selective vertical method to guarantee complete search. CLICKS outperforms previous approaches by over an order of magnitude and scales better than any of the existing method for high-dimensional datasets. We demonstrate this improvement in an excerpt from our comprehensive performance studies.

AB - We present a novel algorithm called CLICKS, that finds clusters in categorical datasets based on a search for k-partite maximal cliques. Unlike previous methods, CLICKS mines subspace clusters. It uses a selective vertical method to guarantee complete search. CLICKS outperforms previous approaches by over an order of magnitude and scales better than any of the existing method for high-dimensional datasets. We demonstrate this improvement in an excerpt from our comprehensive performance studies.

UR - http://www.scopus.com/inward/record.url?scp=28444449780&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=28444449780&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2005.33

DO - 10.1109/ICDE.2005.33

M3 - Conference contribution

SN - 0769522858

SP - 355

EP - 356

BT - Proceedings - International Conference on Data Engineering

ER -