Graph mining for discovering infrastructure patterns in configuration management databases

Pranay Anchuri, Mohammed J. Zaki, Omer Barkol, Ruth Bergman, Yifat Felder, Shahar Golan, Arik Sityon

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

A configuration management database (CMDB) can be considered to be a large graph representing the IT infrastructure entities and their interrelationships. Mining such graphs is challenging because they are large, complex, and multi-attributed and have many repeated labels. These characteristics pose challenges for graph mining algorithms, due to the increased cost of subgraph isomorphism (for support counting) and graph isomorphism (for eliminating duplicate patterns). The notion of pattern frequency or support is also more challenging in a single graph, since it has to be defined in terms of the number of its (potentially, exponentially many) embeddings. We present CMDB-Miner, a novel two-step method for mining infrastructure patterns from CMDB graphs. It first samples the set of maximal frequent patterns and then clusters them to extract the representative infrastructure patterns. We demonstrate the effectiveness of CMDB-Miner on real-world CMDB graphs, as well as synthetic graphs.

Original languageEnglish
Pages (from-to)491-522
Number of pages32
JournalKnowledge and Information Systems
Volume33
Issue number3
DOIs
Publication statusPublished - 9 Aug 2012
Externally publishedYes

Fingerprint

Miners
Labels
Costs

Keywords

  • Configuration management databases
  • Frequent subgraphs
  • Single graph mining
  • Sparse graph mining

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Information Systems
  • Hardware and Architecture
  • Human-Computer Interaction

Cite this

Anchuri, P., Zaki, M. J., Barkol, O., Bergman, R., Felder, Y., Golan, S., & Sityon, A. (2012). Graph mining for discovering infrastructure patterns in configuration management databases. Knowledge and Information Systems, 33(3), 491-522. https://doi.org/10.1007/s10115-012-0528-3

Graph mining for discovering infrastructure patterns in configuration management databases. / Anchuri, Pranay; Zaki, Mohammed J.; Barkol, Omer; Bergman, Ruth; Felder, Yifat; Golan, Shahar; Sityon, Arik.

In: Knowledge and Information Systems, Vol. 33, No. 3, 09.08.2012, p. 491-522.

Research output: Contribution to journalArticle

Anchuri, P, Zaki, MJ, Barkol, O, Bergman, R, Felder, Y, Golan, S & Sityon, A 2012, 'Graph mining for discovering infrastructure patterns in configuration management databases', Knowledge and Information Systems, vol. 33, no. 3, pp. 491-522. https://doi.org/10.1007/s10115-012-0528-3
Anchuri, Pranay ; Zaki, Mohammed J. ; Barkol, Omer ; Bergman, Ruth ; Felder, Yifat ; Golan, Shahar ; Sityon, Arik. / Graph mining for discovering infrastructure patterns in configuration management databases. In: Knowledge and Information Systems. 2012 ; Vol. 33, No. 3. pp. 491-522.
@article{61a2a32788a04f24980b395837365ea2,
title = "Graph mining for discovering infrastructure patterns in configuration management databases",
abstract = "A configuration management database (CMDB) can be considered to be a large graph representing the IT infrastructure entities and their interrelationships. Mining such graphs is challenging because they are large, complex, and multi-attributed and have many repeated labels. These characteristics pose challenges for graph mining algorithms, due to the increased cost of subgraph isomorphism (for support counting) and graph isomorphism (for eliminating duplicate patterns). The notion of pattern frequency or support is also more challenging in a single graph, since it has to be defined in terms of the number of its (potentially, exponentially many) embeddings. We present CMDB-Miner, a novel two-step method for mining infrastructure patterns from CMDB graphs. It first samples the set of maximal frequent patterns and then clusters them to extract the representative infrastructure patterns. We demonstrate the effectiveness of CMDB-Miner on real-world CMDB graphs, as well as synthetic graphs.",
keywords = "Configuration management databases, Frequent subgraphs, Single graph mining, Sparse graph mining",
author = "Pranay Anchuri and Zaki, {Mohammed J.} and Omer Barkol and Ruth Bergman and Yifat Felder and Shahar Golan and Arik Sityon",
year = "2012",
month = "8",
day = "9",
doi = "10.1007/s10115-012-0528-3",
language = "English",
volume = "33",
pages = "491--522",
journal = "Knowledge and Information Systems",
issn = "0219-1377",
publisher = "Springer London",
number = "3",

}

TY - JOUR

T1 - Graph mining for discovering infrastructure patterns in configuration management databases

AU - Anchuri, Pranay

AU - Zaki, Mohammed J.

AU - Barkol, Omer

AU - Bergman, Ruth

AU - Felder, Yifat

AU - Golan, Shahar

AU - Sityon, Arik

PY - 2012/8/9

Y1 - 2012/8/9

N2 - A configuration management database (CMDB) can be considered to be a large graph representing the IT infrastructure entities and their interrelationships. Mining such graphs is challenging because they are large, complex, and multi-attributed and have many repeated labels. These characteristics pose challenges for graph mining algorithms, due to the increased cost of subgraph isomorphism (for support counting) and graph isomorphism (for eliminating duplicate patterns). The notion of pattern frequency or support is also more challenging in a single graph, since it has to be defined in terms of the number of its (potentially, exponentially many) embeddings. We present CMDB-Miner, a novel two-step method for mining infrastructure patterns from CMDB graphs. It first samples the set of maximal frequent patterns and then clusters them to extract the representative infrastructure patterns. We demonstrate the effectiveness of CMDB-Miner on real-world CMDB graphs, as well as synthetic graphs.

AB - A configuration management database (CMDB) can be considered to be a large graph representing the IT infrastructure entities and their interrelationships. Mining such graphs is challenging because they are large, complex, and multi-attributed and have many repeated labels. These characteristics pose challenges for graph mining algorithms, due to the increased cost of subgraph isomorphism (for support counting) and graph isomorphism (for eliminating duplicate patterns). The notion of pattern frequency or support is also more challenging in a single graph, since it has to be defined in terms of the number of its (potentially, exponentially many) embeddings. We present CMDB-Miner, a novel two-step method for mining infrastructure patterns from CMDB graphs. It first samples the set of maximal frequent patterns and then clusters them to extract the representative infrastructure patterns. We demonstrate the effectiveness of CMDB-Miner on real-world CMDB graphs, as well as synthetic graphs.

KW - Configuration management databases

KW - Frequent subgraphs

KW - Single graph mining

KW - Sparse graph mining

UR - http://www.scopus.com/inward/record.url?scp=84869083028&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869083028&partnerID=8YFLogxK

U2 - 10.1007/s10115-012-0528-3

DO - 10.1007/s10115-012-0528-3

M3 - Article

VL - 33

SP - 491

EP - 522

JO - Knowledge and Information Systems

JF - Knowledge and Information Systems

SN - 0219-1377

IS - 3

ER -