Using community information to improve the precision of link prediction methods

Sucheta Soundarajan, John Hopcroft

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

52 Citations (Scopus)

Abstract

Because network data is often incomplete, researchers consider the link prediction problem, which asks which nonexistent edges in an incomplete network are most likely to exist in the complete network. Classical approaches compute the 'similarity' of two nodes, and conclude that highly similar nodes are most likely to be connected in the complete network. Here, we consider several such similarity-based measures, but supplement the similarity calculations with community information. We show that for many networks, the inclusion of community information improves the accuracy of similarity-based link prediction methods. Copyright is held by the author/owner(s).

Original languageEnglish (US)
Title of host publicationWWW'12 - Proceedings of the 21st Annual Conference on World Wide Web Companion
Pages607-608
Number of pages2
DOIs
StatePublished - 2012
Externally publishedYes
Event21st Annual Conference on World Wide Web, WWW'12 - Lyon, France
Duration: Apr 16 2012Apr 20 2012

Other

Other21st Annual Conference on World Wide Web, WWW'12
CountryFrance
CityLyon
Period4/16/124/20/12

Keywords

  • Communities
  • Link prediction
  • Social networks

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Soundarajan, S., & Hopcroft, J. (2012). Using community information to improve the precision of link prediction methods. In WWW'12 - Proceedings of the 21st Annual Conference on World Wide Web Companion (pp. 607-608) https://doi.org/10.1145/2187980.2188150

Using community information to improve the precision of link prediction methods. / Soundarajan, Sucheta; Hopcroft, John.

WWW'12 - Proceedings of the 21st Annual Conference on World Wide Web Companion. 2012. p. 607-608.

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

Soundarajan, S & Hopcroft, J 2012, Using community information to improve the precision of link prediction methods. in WWW'12 - Proceedings of the 21st Annual Conference on World Wide Web Companion. pp. 607-608, 21st Annual Conference on World Wide Web, WWW'12, Lyon, France, 4/16/12. https://doi.org/10.1145/2187980.2188150
Soundarajan S, Hopcroft J. Using community information to improve the precision of link prediction methods. In WWW'12 - Proceedings of the 21st Annual Conference on World Wide Web Companion. 2012. p. 607-608 https://doi.org/10.1145/2187980.2188150
Soundarajan, Sucheta ; Hopcroft, John. / Using community information to improve the precision of link prediction methods. WWW'12 - Proceedings of the 21st Annual Conference on World Wide Web Companion. 2012. pp. 607-608
@inproceedings{6630d949a96b4b78b9b43b6d02814dec,
title = "Using community information to improve the precision of link prediction methods",
abstract = "Because network data is often incomplete, researchers consider the link prediction problem, which asks which nonexistent edges in an incomplete network are most likely to exist in the complete network. Classical approaches compute the 'similarity' of two nodes, and conclude that highly similar nodes are most likely to be connected in the complete network. Here, we consider several such similarity-based measures, but supplement the similarity calculations with community information. We show that for many networks, the inclusion of community information improves the accuracy of similarity-based link prediction methods. Copyright is held by the author/owner(s).",
keywords = "Communities, Link prediction, Social networks",
author = "Sucheta Soundarajan and John Hopcroft",
year = "2012",
doi = "10.1145/2187980.2188150",
language = "English (US)",
isbn = "9781450312301",
pages = "607--608",
booktitle = "WWW'12 - Proceedings of the 21st Annual Conference on World Wide Web Companion",

}

TY - GEN

T1 - Using community information to improve the precision of link prediction methods

AU - Soundarajan, Sucheta

AU - Hopcroft, John

PY - 2012

Y1 - 2012

N2 - Because network data is often incomplete, researchers consider the link prediction problem, which asks which nonexistent edges in an incomplete network are most likely to exist in the complete network. Classical approaches compute the 'similarity' of two nodes, and conclude that highly similar nodes are most likely to be connected in the complete network. Here, we consider several such similarity-based measures, but supplement the similarity calculations with community information. We show that for many networks, the inclusion of community information improves the accuracy of similarity-based link prediction methods. Copyright is held by the author/owner(s).

AB - Because network data is often incomplete, researchers consider the link prediction problem, which asks which nonexistent edges in an incomplete network are most likely to exist in the complete network. Classical approaches compute the 'similarity' of two nodes, and conclude that highly similar nodes are most likely to be connected in the complete network. Here, we consider several such similarity-based measures, but supplement the similarity calculations with community information. We show that for many networks, the inclusion of community information improves the accuracy of similarity-based link prediction methods. Copyright is held by the author/owner(s).

KW - Communities

KW - Link prediction

KW - Social networks

UR - http://www.scopus.com/inward/record.url?scp=84861047529&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861047529&partnerID=8YFLogxK

U2 - 10.1145/2187980.2188150

DO - 10.1145/2187980.2188150

M3 - Conference contribution

AN - SCOPUS:84861047529

SN - 9781450312301

SP - 607

EP - 608

BT - WWW'12 - Proceedings of the 21st Annual Conference on World Wide Web Companion

ER -