{"id":"https://openalex.org/W2057320839","doi":"https://doi.org/10.1145/1189769.1189779","title":"A divide-and-merge methodology for clustering","display_name":"A divide-and-merge methodology for clustering","publication_year":2006,"publication_date":"2006-12-01","ids":{"openalex":"https://openalex.org/W2057320839","doi":"https://doi.org/10.1145/1189769.1189779","mag":"2057320839"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/1189769.1189779","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.cs.yale.edu/homes/kannan/Papers/pods2005.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071379905","display_name":"Chi Cheng","orcid":"https://orcid.org/0000-0001-8596-1801"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Cheng","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA,"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059436381","display_name":"Ravi Kannan","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Kannan","raw_affiliation_strings":["YALE UNIVERSITY, New Haven, CT"],"affiliations":[{"raw_affiliation_string":"YALE UNIVERSITY, New Haven, CT","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111459522","display_name":"Santosh Vempala","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santosh Vempala","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA,"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000511832","display_name":"Grant Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grant Wang","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA,"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA,","institution_ids":["https://openalex.org/I63966007"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.964,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":122,"citation_normalized_percentile":{"value":0.985251,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"31","issue":"4","first_page":"1499","last_page":"1525"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9989,"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"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9989,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9975,"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/T10057","display_name":"Face and Expression Recognition","score":0.9811,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/merge","display_name":"Merge (version control)","score":0.7840004},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.56132543},{"id":"https://openalex.org/keywords/merge-algorithm","display_name":"Merge algorithm","score":0.47034696}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189558},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.7840004},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7545031},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.56132543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5411024},{"id":"https://openalex.org/C140086265","wikidata":"https://www.wikidata.org/wiki/Q11341754","display_name":"Merge algorithm","level":4,"score":0.47034696},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.45460954},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.43930098},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37348926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22050089},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.1461151},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.0},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/1189769.1189779","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.3140","pdf_url":"http://www.cs.yale.edu/homes/kannan/Papers/pods2005.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.3140","pdf_url":"http://www.cs.yale.edu/homes/kannan/Papers/pods2005.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":43,"referenced_works":["https://openalex.org/W1490989942","https://openalex.org/W1492327544","https://openalex.org/W1509381869","https://openalex.org/W1511938660","https://openalex.org/W1521439890","https://openalex.org/W1559013041","https://openalex.org/W1560541823","https://openalex.org/W1601412462","https://openalex.org/W1651093245","https://openalex.org/W1970866964","https://openalex.org/W1971318281","https://openalex.org/W1971784203","https://openalex.org/W1977556410","https://openalex.org/W1981745143","https://openalex.org/W1992419399","https://openalex.org/W1995875735","https://openalex.org/W1996764654","https://openalex.org/W2006283719","https://openalex.org/W2017732166","https://openalex.org/W2034331023","https://openalex.org/W2057712948","https://openalex.org/W2060314721","https://openalex.org/W2070412788","https://openalex.org/W2072211488","https://openalex.org/W2080068757","https://openalex.org/W2081980673","https://openalex.org/W2086917808","https://openalex.org/W2109363337","https://openalex.org/W2110105238","https://openalex.org/W2118587067","https://openalex.org/W2122466336","https://openalex.org/W2122943553","https://openalex.org/W2133576408","https://openalex.org/W2135187880","https://openalex.org/W2139850885","https://openalex.org/W2143654071","https://openalex.org/W2295665070","https://openalex.org/W2602753196","https://openalex.org/W2798909945","https://openalex.org/W4241122026","https://openalex.org/W4245266864","https://openalex.org/W4400191782","https://openalex.org/W89608058"],"related_works":["https://openalex.org/W4220814143","https://openalex.org/W3144143113","https://openalex.org/W2559422900","https://openalex.org/W2384052049","https://openalex.org/W2367205823","https://openalex.org/W2356015003","https://openalex.org/W2171610853","https://openalex.org/W2131625050","https://openalex.org/W2087424554","https://openalex.org/W1997715509"],"abstract_inverted_index":{"We":[0,125,134,152],"present":[1,126],"a":[2,7,13,18,34,39,54,78,127,139],"divide-and-merge":[3],"methodology":[4,145],"for":[5,111,116],"clustering":[6,36,41],"set":[8],"of":[9,61,77,131,138],"objects":[10],"that":[11,90,107,142],"combines":[12],"top-down":[14,28],"\u201cdivide\u201d":[15],"phase":[16,101],"with":[17],"bottom-up":[19,30],"\u201cmerge\u201d":[20],"phase.":[21],"In":[22],"contrast,":[23],"previous":[24],"algorithms":[25],"use":[26],"either":[27],"or":[29,37],"methods":[31],"to":[32,85,146],"construct":[33],"hierarchical":[35],"produce":[38],"flat":[40],"using":[42],"local":[43],"search":[44],"(e.g.,":[45],"k":[46,118],"-means).":[47],"For":[48],"the":[49,59,62,71,75,87,104,109,132,136],"divide":[50],"phase,":[51],"which":[52],"produces":[53],"tree":[55,110],"whose":[56],"leaves":[57],"are":[58],"elements":[60],"set,":[63],"we":[64,82],"suggest":[65],"an":[66],"efficient":[67],"spectral":[68],"algorithm.":[69],"When":[70],"data":[72],"is":[73],"in":[74,96],"form":[76],"sparse":[79],"document-term":[80],"matrix,":[81],"show":[83],"how":[84],"modify":[86],"algorithm":[88],"so":[89],"it":[91],"maintains":[92],"sparsity":[93],"and":[94],"runs":[95],"linear":[97],"space.":[98],"The":[99],"merge":[100],"quickly":[102],"finds":[103],"optimal":[105],"partition":[106],"respects":[108],"many":[112],"natural":[113],"objective":[114],"functions,":[115],"example,":[117],"-means,":[119],"min-diameter,":[120],"min-sum,":[121],"correlation":[122],"clustering,":[123],"etc.":[124],"thorough":[128],"experimental":[129],"evaluation":[130],"methodology.":[133],"describe":[135],"implementation":[137],"meta-search":[140],"engine":[141],"uses":[143],"this":[144],"cluster":[147],"results":[148,157],"from":[149],"web":[150],"searches.":[151],"also":[153],"give":[154],"comparative":[155],"empirical":[156],"on":[158],"several":[159],"real":[160],"datasets.":[161]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2057320839","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":10}],"updated_date":"2024-12-24T14:56:38.752787","created_date":"2016-06-24"}