Output space sampling for graph patterns

Mohammad Al Hasan, Mohammed J. Zaki

Research output: Chapter in Book/Report/Conference proceedingChapter

76 Citations (Scopus)

Abstract

Recent interest in graph pattern mining has shifted from finding all frequent subgraphs to obtaining a small subset of frequent subgraphs that are representative, discriminative or significant. The main motivation behind that is to cope with the scalability problem that the graph mining algorithms suffer when mining databases of large graphs. Another motivation is to obtain a succinct output set that is informative and useful. In the same spirit, researchers also proposed sampling based algorithms that sample the output space of the frequent patterns to obtain representative subgraphs. In this work, we propose a generic sampling framework that is based on Metropolis-Hastings algorithm to sample the output space of frequent subgraphs. Our experiments on various sampling strategies show the versatility, utility and efficiency of the proposed sampling approach.

Original languageEnglish
Title of host publicationProceedings of the VLDB Endowment
Pages730-741
Number of pages12
Volume2
Edition1
Publication statusPublished - 2009
Externally publishedYes

Fingerprint

Sampling
Scalability
Experiments

ASJC Scopus subject areas

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

Cite this

Al Hasan, M., & Zaki, M. J. (2009). Output space sampling for graph patterns. In Proceedings of the VLDB Endowment (1 ed., Vol. 2, pp. 730-741)

Output space sampling for graph patterns. / Al Hasan, Mohammad; Zaki, Mohammed J.

Proceedings of the VLDB Endowment. Vol. 2 1. ed. 2009. p. 730-741.

Research output: Chapter in Book/Report/Conference proceedingChapter

Al Hasan, M & Zaki, MJ 2009, Output space sampling for graph patterns. in Proceedings of the VLDB Endowment. 1 edn, vol. 2, pp. 730-741.
Al Hasan M, Zaki MJ. Output space sampling for graph patterns. In Proceedings of the VLDB Endowment. 1 ed. Vol. 2. 2009. p. 730-741
Al Hasan, Mohammad ; Zaki, Mohammed J. / Output space sampling for graph patterns. Proceedings of the VLDB Endowment. Vol. 2 1. ed. 2009. pp. 730-741
@inbook{800680a4232f454eba40d5a36b0396c5,
title = "Output space sampling for graph patterns",
abstract = "Recent interest in graph pattern mining has shifted from finding all frequent subgraphs to obtaining a small subset of frequent subgraphs that are representative, discriminative or significant. The main motivation behind that is to cope with the scalability problem that the graph mining algorithms suffer when mining databases of large graphs. Another motivation is to obtain a succinct output set that is informative and useful. In the same spirit, researchers also proposed sampling based algorithms that sample the output space of the frequent patterns to obtain representative subgraphs. In this work, we propose a generic sampling framework that is based on Metropolis-Hastings algorithm to sample the output space of frequent subgraphs. Our experiments on various sampling strategies show the versatility, utility and efficiency of the proposed sampling approach.",
author = "{Al Hasan}, Mohammad and Zaki, {Mohammed J.}",
year = "2009",
language = "English",
volume = "2",
pages = "730--741",
booktitle = "Proceedings of the VLDB Endowment",
edition = "1",

}

TY - CHAP

T1 - Output space sampling for graph patterns

AU - Al Hasan, Mohammad

AU - Zaki, Mohammed J.

PY - 2009

Y1 - 2009

N2 - Recent interest in graph pattern mining has shifted from finding all frequent subgraphs to obtaining a small subset of frequent subgraphs that are representative, discriminative or significant. The main motivation behind that is to cope with the scalability problem that the graph mining algorithms suffer when mining databases of large graphs. Another motivation is to obtain a succinct output set that is informative and useful. In the same spirit, researchers also proposed sampling based algorithms that sample the output space of the frequent patterns to obtain representative subgraphs. In this work, we propose a generic sampling framework that is based on Metropolis-Hastings algorithm to sample the output space of frequent subgraphs. Our experiments on various sampling strategies show the versatility, utility and efficiency of the proposed sampling approach.

AB - Recent interest in graph pattern mining has shifted from finding all frequent subgraphs to obtaining a small subset of frequent subgraphs that are representative, discriminative or significant. The main motivation behind that is to cope with the scalability problem that the graph mining algorithms suffer when mining databases of large graphs. Another motivation is to obtain a succinct output set that is informative and useful. In the same spirit, researchers also proposed sampling based algorithms that sample the output space of the frequent patterns to obtain representative subgraphs. In this work, we propose a generic sampling framework that is based on Metropolis-Hastings algorithm to sample the output space of frequent subgraphs. Our experiments on various sampling strategies show the versatility, utility and efficiency of the proposed sampling approach.

UR - http://www.scopus.com/inward/record.url?scp=84865096110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865096110&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:84865096110

VL - 2

SP - 730

EP - 741

BT - Proceedings of the VLDB Endowment

ER -