{"id":"https://openalex.org/W2108399535","doi":"https://doi.org/10.14778/2180912.2180915","title":"Scalable k-means++","display_name":"Scalable k-means++","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2108399535","doi":"https://doi.org/10.14778/2180912.2180915","mag":"2108399535"},"language":"en","primary_location":{"id":"doi:10.14778/2180912.2180915","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2180912.2180915","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/A5074192084","display_name":"Bahman Bahmani","orcid":"https://orcid.org/0000-0001-5485-3314"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bahman Bahmani","raw_affiliation_strings":["Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044201440","display_name":"Benjamin Moseley","orcid":"https://orcid.org/0000-0001-8162-017X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Moseley","raw_affiliation_strings":["University of Illinois, Urbana, IL","[University of Illinois, Urbana, IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana, IL","institution_ids":["https://openalex.org/I2801919071"]},{"raw_affiliation_string":"[University of Illinois, Urbana, IL]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057347957","display_name":"Andrea Vattani","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Vattani","raw_affiliation_strings":["University of California, San Diego, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego, CA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101772779","display_name":"Ravi Kumar","orcid":"https://orcid.org/0000-0002-2203-2586"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ravi Kumar","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA","Yahoo Research, Sunnyvale, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo Research, Sunnyvale, CA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070795618","display_name":"Sergei Vassilvitskii","orcid":"https://orcid.org/0000-0003-0235-1624"},"institutions":[{"id":"https://openalex.org/I4210133173","display_name":"Research!America (United States)","ror":"https://ror.org/044pgyv50","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133173"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergei Vassilvitskii","raw_affiliation_strings":["Yahoo! Research, New York, NY","Yahoo Research, New York, NY,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, New York, NY","institution_ids":["https://openalex.org/I4210133173","https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo Research, New York, NY,","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074192084"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":21.2939,"has_fulltext":false,"cited_by_count":633,"citation_normalized_percentile":{"value":0.99677419,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"5","issue":"7","first_page":"622","last_page":"633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9921000003814697,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9896000027656555,"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/initialization","display_name":"Initialization","score":0.9775918126106262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7713229656219482},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.698185384273529},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6386334896087646},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.6299208998680115},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5671094059944153},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.538976788520813},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4627537727355957},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34712982177734375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.184227854013443}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.9775918126106262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7713229656219482},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.698185384273529},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6386334896087646},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6299208998680115},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5671094059944153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.538976788520813},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4627537727355957},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34712982177734375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.184227854013443},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2180912.2180915","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2180912.2180915","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W147860157","https://openalex.org/W1501500081","https://openalex.org/W1598064945","https://openalex.org/W1870625491","https://openalex.org/W1992419399","https://openalex.org/W1998325344","https://openalex.org/W1998739300","https://openalex.org/W2006685053","https://openalex.org/W2034616054","https://openalex.org/W2048442462","https://openalex.org/W2051109346","https://openalex.org/W2051586153","https://openalex.org/W2064029323","https://openalex.org/W2073459066","https://openalex.org/W2086959852","https://openalex.org/W2095897464","https://openalex.org/W2110105238","https://openalex.org/W2116762767","https://openalex.org/W2121737596","https://openalex.org/W2122465391","https://openalex.org/W2123297508","https://openalex.org/W2123427850","https://openalex.org/W2129565593","https://openalex.org/W2131220986","https://openalex.org/W2131687179","https://openalex.org/W2132958733","https://openalex.org/W2140414913","https://openalex.org/W2142827986","https://openalex.org/W2142838865","https://openalex.org/W2144405306","https://openalex.org/W2148372359","https://openalex.org/W2153977620","https://openalex.org/W2156499390","https://openalex.org/W2174057495","https://openalex.org/W2199495299","https://openalex.org/W2741690731","https://openalex.org/W2950437976","https://openalex.org/W4231029117","https://openalex.org/W4236385439","https://openalex.org/W6683136438"],"related_works":["https://openalex.org/W3176564347","https://openalex.org/W3031039437","https://openalex.org/W3204184292","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3101398262","https://openalex.org/W3095877357","https://openalex.org/W10861731","https://openalex.org/W2008332083","https://openalex.org/W2050451745"],"abstract_inverted_index":{"Over":[0],"half":[1],"a":[2,25,35,91,115,148,153,164],"century":[3],"old":[4],"and":[5,158,186],"showing":[6],"no":[7],"signs":[8],"of":[9,15,28,52,65,95,108,135,156,167],"aging,":[10],"k":[11,29,42,67,84,125,136,145,178,181],"-means":[12,30,126],"remains":[13],"one":[14,81],"the":[16,59,66,87,106,132],"most":[17],"popular":[18],"data":[19,88,175],"processing":[20],"algorithms.":[21],"As":[22],"is":[23,31,55,69,119],"well-known,":[24],"proper":[26],"initialization":[27,44,143],"crucial":[32],"for":[33],"obtaining":[34,48],"good":[36,92,116],"final":[37],"solution.":[38,61],"The":[39],"recently":[40],"proposed":[41,142],"-means++":[43,68,182],"algorithm":[45,144],"achieves":[46],"this,":[47],"an":[49],"initial":[50,93],"set":[51,94],"centers":[53],"that":[54,127,140,161,177],"provably":[56],"close":[57],"to":[58,78,89,103,111],"optimum":[60],"A":[62],"major":[63],"downside":[64],"its":[70,76],"inherent":[71],"sequential":[72,185],"nature,":[73],"which":[74],"limits":[75],"applicability":[77],"massive":[79],"data:":[80],"must":[82],"make":[83],"passes":[85,109,168],"over":[86],"find":[90],"centers.":[96],"In":[97],"this":[98],"work":[99],"we":[100],"show":[101,160],"how":[102],"drastically":[104],"reduce":[105],"number":[107,155,166],"needed":[110],"obtain,":[112],"in":[113,162,183],"parallel,":[114],"initialization.":[117],"This":[118],"unlike":[120],"prevailing":[121],"efforts":[122],"on":[123,131,172],"parallelizing":[124],"have":[128],"mostly":[129],"focused":[130],"post-initialization":[133],"phases":[134],"-means.":[137],"We":[138],"prove":[139],"our":[141],"-means||":[146,179],"obtains":[147],"nearly":[149],"optimal":[150],"solution":[151],"after":[152],"logarithmic":[154],"passes,":[157],"then":[159],"practice":[163],"constant":[165],"suffices.":[169],"Experimental":[170],"evaluation":[171],"real-world":[173],"large-scale":[174],"demonstrates":[176],"outperforms":[180],"both":[184],"parallel":[187],"settings.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":50},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":48},{"year":2020,"cited_by_count":70},{"year":2019,"cited_by_count":72},{"year":2018,"cited_by_count":57},{"year":2017,"cited_by_count":60},{"year":2016,"cited_by_count":65},{"year":2015,"cited_by_count":33},{"year":2014,"cited_by_count":35},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2016-06-24T00:00:00"}