Mining attributestructure correlated patterns in large attributed graphs

Arlei Silva, Wagner Meira, Mohammed J. Zaki

Research output: Chapter in Book/Report/Conference proceedingChapter

80 Citations (Scopus)

Abstract

In this work, we study the correlation between attribute sets and the occurrence of dense subgraphs in large attributed graphs, a task we call structural correlation pattern mining. A structural correlation pattern is a dense subgraph induced by a particular attribute set. Existing methods are not able to extract relevant knowledge regarding how vertex attributes interact with dense subgraphs. Structural correlation pattern mining combines aspects of frequent itemset and quasi-clique mining problems. We propose statistical significance measures that compare the structural correlation of attribute sets against their expected values using null models. Moreover, we evaluate the interestingness of structural correlation patterns in terms of size and density. An effcient algorithm that combines search and pruning strategies in the identification of the most relevant structural correlation patterns is presented. We apply our method for the analysis of three real-world attributed graphs: a collaboration, a music, and a citation network, verifying that it provides valuable knowledge in a feasible time.

Original languageEnglish
Title of host publicationProceedings of the VLDB Endowment
Pages466-477
Number of pages12
Volume5
Edition5
Publication statusPublished - Jan 2012
Externally publishedYes

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computer Science(all)

Cite this

Silva, A., Meira, W., & Zaki, M. J. (2012). Mining attributestructure correlated patterns in large attributed graphs. In Proceedings of the VLDB Endowment (5 ed., Vol. 5, pp. 466-477)

Mining attributestructure correlated patterns in large attributed graphs. / Silva, Arlei; Meira, Wagner; Zaki, Mohammed J.

Proceedings of the VLDB Endowment. Vol. 5 5. ed. 2012. p. 466-477.

Research output: Chapter in Book/Report/Conference proceedingChapter

Silva, A, Meira, W & Zaki, MJ 2012, Mining attributestructure correlated patterns in large attributed graphs. in Proceedings of the VLDB Endowment. 5 edn, vol. 5, pp. 466-477.
Silva A, Meira W, Zaki MJ. Mining attributestructure correlated patterns in large attributed graphs. In Proceedings of the VLDB Endowment. 5 ed. Vol. 5. 2012. p. 466-477
Silva, Arlei ; Meira, Wagner ; Zaki, Mohammed J. / Mining attributestructure correlated patterns in large attributed graphs. Proceedings of the VLDB Endowment. Vol. 5 5. ed. 2012. pp. 466-477
@inbook{8dd3fcf2f5a74e798f43351a3df319d3,
title = "Mining attributestructure correlated patterns in large attributed graphs",
abstract = "In this work, we study the correlation between attribute sets and the occurrence of dense subgraphs in large attributed graphs, a task we call structural correlation pattern mining. A structural correlation pattern is a dense subgraph induced by a particular attribute set. Existing methods are not able to extract relevant knowledge regarding how vertex attributes interact with dense subgraphs. Structural correlation pattern mining combines aspects of frequent itemset and quasi-clique mining problems. We propose statistical significance measures that compare the structural correlation of attribute sets against their expected values using null models. Moreover, we evaluate the interestingness of structural correlation patterns in terms of size and density. An effcient algorithm that combines search and pruning strategies in the identification of the most relevant structural correlation patterns is presented. We apply our method for the analysis of three real-world attributed graphs: a collaboration, a music, and a citation network, verifying that it provides valuable knowledge in a feasible time.",
author = "Arlei Silva and Wagner Meira and Zaki, {Mohammed J.}",
year = "2012",
month = "1",
language = "English",
volume = "5",
pages = "466--477",
booktitle = "Proceedings of the VLDB Endowment",
edition = "5",

}

TY - CHAP

T1 - Mining attributestructure correlated patterns in large attributed graphs

AU - Silva, Arlei

AU - Meira, Wagner

AU - Zaki, Mohammed J.

PY - 2012/1

Y1 - 2012/1

N2 - In this work, we study the correlation between attribute sets and the occurrence of dense subgraphs in large attributed graphs, a task we call structural correlation pattern mining. A structural correlation pattern is a dense subgraph induced by a particular attribute set. Existing methods are not able to extract relevant knowledge regarding how vertex attributes interact with dense subgraphs. Structural correlation pattern mining combines aspects of frequent itemset and quasi-clique mining problems. We propose statistical significance measures that compare the structural correlation of attribute sets against their expected values using null models. Moreover, we evaluate the interestingness of structural correlation patterns in terms of size and density. An effcient algorithm that combines search and pruning strategies in the identification of the most relevant structural correlation patterns is presented. We apply our method for the analysis of three real-world attributed graphs: a collaboration, a music, and a citation network, verifying that it provides valuable knowledge in a feasible time.

AB - In this work, we study the correlation between attribute sets and the occurrence of dense subgraphs in large attributed graphs, a task we call structural correlation pattern mining. A structural correlation pattern is a dense subgraph induced by a particular attribute set. Existing methods are not able to extract relevant knowledge regarding how vertex attributes interact with dense subgraphs. Structural correlation pattern mining combines aspects of frequent itemset and quasi-clique mining problems. We propose statistical significance measures that compare the structural correlation of attribute sets against their expected values using null models. Moreover, we evaluate the interestingness of structural correlation patterns in terms of size and density. An effcient algorithm that combines search and pruning strategies in the identification of the most relevant structural correlation patterns is presented. We apply our method for the analysis of three real-world attributed graphs: a collaboration, a music, and a citation network, verifying that it provides valuable knowledge in a feasible time.

UR - http://www.scopus.com/inward/record.url?scp=84863729772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863729772&partnerID=8YFLogxK

M3 - Chapter

VL - 5

SP - 466

EP - 477

BT - Proceedings of the VLDB Endowment

ER -