{"id":"https://openalex.org/W2070422353","doi":"https://doi.org/10.14778/1920841.1920930","title":"Scalable discovery of best clusters on large graphs","display_name":"Scalable discovery of best clusters on large graphs","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2070422353","doi":"https://doi.org/10.14778/1920841.1920930","mag":"2070422353"},"language":"en","primary_location":{"id":"doi:10.14778/1920841.1920930","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920930","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070011635","display_name":"Kathy Macropol","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathy Macropol","raw_affiliation_strings":["University of California, Santa Barbara, CA","University of California, Santa Barbara, Ca#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, CA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California, Santa Barbara, Ca#TAB#","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036639779","display_name":"Ambuj K. Singh","orcid":"https://orcid.org/0000-0002-1997-7140"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ambuj Singh","raw_affiliation_strings":["University of California, Santa Barbara, CA","University of California, Santa Barbara, Ca#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, CA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California, Santa Barbara, Ca#TAB#","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":1.7452,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.83903996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"3","issue":"1-2","first_page":"693","last_page":"702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parallelizable-manifold","display_name":"Parallelizable manifold","score":0.857529878616333},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7364050149917603},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7161086797714233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7088660001754761},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5052655339241028},{"id":"https://openalex.org/keywords/clustering-coefficient","display_name":"Clustering coefficient","score":0.4924827516078949},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4703056216239929},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3135761618614197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19023388624191284}],"concepts":[{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.857529878616333},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7364050149917603},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7161086797714233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7088660001754761},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5052655339241028},{"id":"https://openalex.org/C22047676","wikidata":"https://www.wikidata.org/wiki/Q898680","display_name":"Clustering coefficient","level":3,"score":0.4924827516078949},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4703056216239929},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3135761618614197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19023388624191284},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/1920841.1920930","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920930","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.5848","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.5848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/%7Evldb2010/proceedings/files/papers/R62.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6399999856948853,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1482680420","https://openalex.org/W1502916507","https://openalex.org/W1530495682","https://openalex.org/W1664520935","https://openalex.org/W1783384641","https://openalex.org/W1991645955","https://openalex.org/W1993091968","https://openalex.org/W2034331023","https://openalex.org/W2057272970","https://openalex.org/W2057793636","https://openalex.org/W2074755764","https://openalex.org/W2086254934","https://openalex.org/W2103017472","https://openalex.org/W2105060667","https://openalex.org/W2105535951","https://openalex.org/W2113613324","https://openalex.org/W2121564430","https://openalex.org/W2121947440","https://openalex.org/W2127048411","https://openalex.org/W2131183411","https://openalex.org/W2135512436","https://openalex.org/W2135957668","https://openalex.org/W2136850043","https://openalex.org/W2142517301","https://openalex.org/W2146591355","https://openalex.org/W2149857793","https://openalex.org/W2150442700","https://openalex.org/W2152360905","https://openalex.org/W2152565070","https://openalex.org/W2173213060","https://openalex.org/W2319009107","https://openalex.org/W2952395520","https://openalex.org/W3102641634"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W4285069850"],"abstract_inverted_index":{"The":[0,96],"identification":[1],"of":[2,42,58,135],"clusters,":[3,60],"well-connected":[4],"components":[5],"in":[6,11,40,65,93,159],"a":[7,74,113],"graph,":[8],"is":[9,49,98,102,115],"useful":[10],"many":[12,51],"applications":[13,53],"from":[14],"biological":[15],"function":[16],"prediction":[17],"to":[18,104,137,155],"social":[19],"community":[20],"detection.":[21],"However,":[22],"finding":[23],"these":[24],"clusters":[25,64,92,148],"can":[26],"be":[27,156],"difficult":[28],"as":[29],"graph":[30,35],"sizes":[31],"increase.":[32],"Most":[33],"current":[34],"clustering":[36,52,128],"algorithms":[37],"scale":[38,141],"poorly":[39],"terms":[41],"time":[43,133],"or":[44],"memory.":[45],"An":[46],"important":[47],"insight":[48],"that":[50,117],"need":[54],"only":[55],"the":[56,66,147],"subset":[57],"best":[59,91],"and":[61,101,162],"not":[62],"all":[63],"entire":[67],"graph.":[68],"In":[69,145],"this":[70],"paper":[71],"we":[72],"propose":[73],"new":[75],"technique,":[76],"Top":[77],"Graph":[78],"Clusters":[79],"(TopGC),":[80],"which":[81],"probabilistically":[82],"searches":[83],"large,":[84],"edge":[85],"weighted,":[86],"directed":[87],"graphs":[88],"for":[89],"their":[90],"linear":[94],"time.":[95],"algorithm":[97],"inherently":[99],"parallelizable,":[100],"able":[103],"find":[105],"variable":[106],"size,":[107],"overlapping":[108],"clusters.":[109],"To":[110],"increase":[111],"scalability,":[112],"parameter":[114],"introduced":[116],"controls":[118],"memory":[119],"use.":[120],"When":[121],"compared":[122,164],"with":[123],"three":[124],"other":[125],"state-of-the":[126],"art":[127],"techniques,":[129],"TopGC":[130,151],"achieves":[131],"running":[132],"speedups":[134],"up":[136],"70%":[138],"on":[139,165],"large":[140],"real":[142,166],"world":[143,167],"datasets.":[144],"addition,":[146],"returned":[149],"by":[150],"are":[152],"consistently":[153],"found":[154],"better":[157],"both":[158],"calculated":[160],"score":[161],"when":[163],"benchmarks.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}