{"id":"https://openalex.org/W1491215891","doi":"https://doi.org/10.1109/icdm.2003.1250980","title":"Tractable group detection on large link data sets","display_name":"Tractable group detection on large link data sets","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W1491215891","doi":"https://doi.org/10.1109/icdm.2003.1250980","mag":"1491215891"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2003.1250980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-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/A5042115859","display_name":"Jeremy Kubica","orcid":"https://orcid.org/0009-0009-2281-7031"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Kubica","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Robotics Institute, Carnegie Mellon University,Pittsburgh,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101927521","display_name":"Andrew Moore","orcid":"https://orcid.org/0000-0002-3395-0841"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Moore","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103053567","display_name":"J. Schneider","orcid":"https://orcid.org/0000-0002-8653-9220"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Schneider","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2373,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.77716269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"573","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9965999722480774,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9944000244140625,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.7004687786102295},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6884405612945557},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5583977699279785},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.5128598213195801},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4551312029361725},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44721272587776184},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.4423021972179413},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42728424072265625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36284154653549194},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3372142016887665},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32697391510009766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3208119869232178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7004687786102295},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6884405612945557},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5583977699279785},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.5128598213195801},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4551312029361725},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44721272587776184},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.4423021972179413},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42728424072265625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36284154653549194},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3372142016887665},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32697391510009766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3208119869232178},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdm.2003.1250980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.88.1161","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.88.1161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~jkubica/papers/kgroups_ICDM.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.4990","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.4990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~jkubica/papers/kgroupsTR.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W793800663","https://openalex.org/W1634005169","https://openalex.org/W1880262756","https://openalex.org/W1968949570","https://openalex.org/W2057712948","https://openalex.org/W2097089247","https://openalex.org/W2114759290"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Discovering":[0],"underlying":[1,40],"structure":[2],"from":[3,44],"co-occurrence":[4,45],"data":[5,81],"is":[6,49,72,133],"an":[7,36,90,94],"important":[8],"task":[9],"in":[10,70,130,139],"a":[11,52,122],"variety":[12,123],"of":[13,42,99,106,117,124],"fields,":[14],"including:":[15],"insurance,":[16],"intelligence,":[17],"criminal":[18],"investigation,":[19],"epidemiology,":[20],"human":[21],"resources,":[22],"and":[23,56,119],"marketing.":[24],"Previously":[25],"Kubica":[26],"et":[27],"al.":[28],"presented":[29],"the":[30,67,104,115],"group":[31],"detection":[32],"algorithm":[33,37,48,91],"(GDA)":[34],"-":[35,89],"for":[38,78],"finding":[39],"groupings":[41],"entities":[43],"data.":[46],"This":[47],"based":[50],"on":[51,121],"probabilistic":[53,111],"generative":[54],"model":[55],"produces":[57],"coherent":[58],"groups":[59,107],"that":[60,92,98,127],"are":[61],"consistent":[62],"with":[63],"prior":[64],"knowledge.":[65],"Unfortunately,":[66],"optimization":[68],"used":[69],"GDA":[71,118],"slow,":[73],"potentially":[74],"making":[75],"it":[76],"infeasible":[77],"many":[79],"large":[80],"sets.":[82],"To":[83],"this":[84],"end,":[85],"we":[86],"present":[87],"k-groups":[88,120],"uses":[93],"approach":[95],"similar":[96],"to":[97,101],"k-means":[100],"significantly":[102,134],"accelerate":[103],"discovery":[105],"while":[108],"retaining":[109],"GDA's":[110],"model.":[112],"We":[113],"compare":[114],"performance":[116],"data,":[125],"showing":[126],"k-groups'":[128],"sacrifice":[129],"solution":[131],"quality":[132],"offset":[135],"by":[136],"its":[137],"increase":[138],"speed.":[140]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}