Show simple item record

dc.contributor.authorEmmons, Scott
dc.contributor.authorKobourov, Stephen
dc.contributor.authorGallant, Mike
dc.contributor.authorBörner, Katy
dc.date.accessioned2016-08-27T01:06:49Z
dc.date.available2016-08-27T01:06:49Z
dc.date.issued2016-07-08
dc.identifier.citationAnalysis of Network Clustering Algorithms and Cluster Quality Metrics at Scale 2016, 11 (7):e0159161 PLOS ONEen
dc.identifier.issn1932-6203
dc.identifier.doi10.1371/journal.pone.0159161
dc.identifier.urihttp://hdl.handle.net/10150/618984
dc.description.abstractOverview Notions of community quality underlie the clustering of networks. While studies surrounding network clustering are increasingly common, a precise understanding of the realtionship between different cluster quality metrics is unknown. In this paper, we examine the relationship between stand-alone cluster quality metrics and information recovery metrics through a rigorous analysis of four widely-used network clustering algorithms-Louvain, Infomap, label propagation, and smart local moving. We consider the stand-alone quality metrics of modularity, conductance, and coverage, and we consider the information recovery metrics of adjusted Rand score, normalized mutual information, and a variant of normalized mutual information used in previous work. Our study includes both synthetic graphs and empirical data sets of sizes varying from 1,000 to 1,000,000 nodes. Cluster Quality Metrics We find significant differences among the results of the different cluster quality metrics. For example, clustering algorithms can return a value of 0.4 out of 1 onmodularity but score 0 out of 1 on information recovery. We find conductance, though imperfect, to be the stand-alone quality metric that best indicates performance on the information recovery metrics. Additionally, our study shows that the variant of normalized mutual information used in previous work cannot be assumed to differ only slightly from traditional normalized mutual information. Network Clustering Algorithms Smart local moving is the overall best performing algorithm in our study, but discrepancies between cluster evaluation metrics prevent us from declaring it an absolutely superior algorithm. Interestingly, Louvain performed better than Infomap in nearly all the tests in our study, contradicting the results of previous work in which Infomap was superior to Louvain. We find that although label propagation performs poorly when clusters are less clearly defined, it scales efficiently and accurately to large graphs with well-defined clusters.
dc.description.sponsorshipNational Institutes of Health; Lilly Endowment, Inc.; Indiana METACyt Initiativeen
dc.language.isoenen
dc.publisherPublic Library of Scienceen
dc.relation.urlhttp://dx.plos.org/10.1371/journal.pone.0159161en
dc.rights© 2016 Emmons et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.en
dc.titleAnalysis of Network Clustering Algorithms and Cluster Quality Metrics at Scaleen
dc.typeArticleen
dc.contributor.departmentUniv Arizona, Dept Comp Scien
dc.identifier.journalPLOS ONEen
dc.description.noteOpen Access Journalen
dc.description.collectioninformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.en
dc.eprint.versionFinal published versionen
refterms.dateFOA2018-08-13T16:03:03Z
html.description.abstractOverview Notions of community quality underlie the clustering of networks. While studies surrounding network clustering are increasingly common, a precise understanding of the realtionship between different cluster quality metrics is unknown. In this paper, we examine the relationship between stand-alone cluster quality metrics and information recovery metrics through a rigorous analysis of four widely-used network clustering algorithms-Louvain, Infomap, label propagation, and smart local moving. We consider the stand-alone quality metrics of modularity, conductance, and coverage, and we consider the information recovery metrics of adjusted Rand score, normalized mutual information, and a variant of normalized mutual information used in previous work. Our study includes both synthetic graphs and empirical data sets of sizes varying from 1,000 to 1,000,000 nodes. Cluster Quality Metrics We find significant differences among the results of the different cluster quality metrics. For example, clustering algorithms can return a value of 0.4 out of 1 onmodularity but score 0 out of 1 on information recovery. We find conductance, though imperfect, to be the stand-alone quality metric that best indicates performance on the information recovery metrics. Additionally, our study shows that the variant of normalized mutual information used in previous work cannot be assumed to differ only slightly from traditional normalized mutual information. Network Clustering Algorithms Smart local moving is the overall best performing algorithm in our study, but discrepancies between cluster evaluation metrics prevent us from declaring it an absolutely superior algorithm. Interestingly, Louvain performed better than Infomap in nearly all the tests in our study, contradicting the results of previous work in which Infomap was superior to Louvain. We find that although label propagation performs poorly when clusters are less clearly defined, it scales efficiently and accurately to large graphs with well-defined clusters.


Files in this item

Thumbnail
Name:
journal.pone.0159161.PDF
Size:
3.172Mb
Format:
PDF
Description:
Final Published Version

This item appears in the following Collection(s)

Show simple item record