SimRank: a measure of structural-context similarity
G. Jeh, and J. Widom. KDD '02: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, page 538--543. New York, NY, USA, ACM, (2002)
DOI: 10.1145/775047.775126
Abstract
The problem of measuring "similarity" of objects arises in many applications, and many domain-specific measures have been developed, e.g., matching text across documents or computing overlap among item-sets. We propose a complementary approach, applicable in any domain with object-to-object relationships, that measures similarity of the structural context in which objects occur, based on their relationships with other objects. Effectively, we compute a measure that says "two objects are similar if they are related to similar objects:" This general similarity measure, called SimRank , is based on a simple and intuitive graph-theoretic model. For a given domain, SimRank can be combined with other domain-specific similarity measures. We suggest techniques for efficient computation of SimRank scores, and provide experimental results on two application domains showing the computational feasibility and effectiveness of our approach.
%0 Conference Paper
%1 citeulike:349900
%A Jeh, Glen
%A Widom, Jennifer
%B KDD '02: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
%C New York, NY, USA
%D 2002
%I ACM
%K clustering, web-graph
%P 538--543
%R 10.1145/775047.775126
%T SimRank: a measure of structural-context similarity
%U http://dx.doi.org/10.1145/775047.775126
%X The problem of measuring "similarity" of objects arises in many applications, and many domain-specific measures have been developed, e.g., matching text across documents or computing overlap among item-sets. We propose a complementary approach, applicable in any domain with object-to-object relationships, that measures similarity of the structural context in which objects occur, based on their relationships with other objects. Effectively, we compute a measure that says "two objects are similar if they are related to similar objects:" This general similarity measure, called SimRank , is based on a simple and intuitive graph-theoretic model. For a given domain, SimRank can be combined with other domain-specific similarity measures. We suggest techniques for efficient computation of SimRank scores, and provide experimental results on two application domains showing the computational feasibility and effectiveness of our approach.
%@ 1-58113-567-X
@inproceedings{citeulike:349900,
abstract = {The problem of measuring "similarity" of objects arises in many applications, and many domain-specific measures have been developed, e.g., matching text across documents or computing overlap among item-sets. We propose a complementary approach, applicable in any domain with object-to-object relationships, that measures similarity of the structural context in which objects occur, based on their relationships with other objects. Effectively, we compute a measure that says "two objects are similar if they are related to similar objects:" This general similarity measure, called SimRank , is based on a simple and intuitive graph-theoretic model. For a given domain, SimRank can be combined with other domain-specific similarity measures. We suggest techniques for efficient computation of SimRank scores, and provide experimental results on two application domains showing the computational feasibility and effectiveness of our approach.},
added-at = {2009-08-06T15:16:38.000+0200},
address = {New York, NY, USA},
author = {Jeh, Glen and Widom, Jennifer},
biburl = {https://www.bibsonomy.org/bibtex/29b901eee9786a06b6ef7203e7a920608/chato},
booktitle = {KDD '02: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining},
citeulike-article-id = {349900},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=775126},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/775047.775126},
doi = {10.1145/775047.775126},
interhash = {a6d4531690305dc44937118df813b4b5},
intrahash = {9b901eee9786a06b6ef7203e7a920608},
isbn = {1-58113-567-X},
keywords = {clustering, web-graph},
location = {Edmonton, Alberta, Canada},
pages = {538--543},
posted-at = {2006-06-05 15:49:45},
priority = {0},
publisher = {ACM},
timestamp = {2009-08-06T15:16:52.000+0200},
title = {SimRank: a measure of structural-context similarity},
url = {http://dx.doi.org/10.1145/775047.775126},
year = 2002
}