{"id":"https://openalex.org/W2069564486","doi":"https://doi.org/10.1109/tpds.2014.2306193","title":"Efficient &lt;inline-formula&gt;&lt;tex-math&gt;$k$&lt;/tex-math&gt;&lt;alternatives&gt; &lt;inline-graphic xlink:type=\"simple\" xlink:href=\"qu-ieq1-2306193.gif\"/&gt;&lt;/alternatives&gt;&lt;/inline-formula&gt;-Means++ Approximation with MapReduce","display_name":"Efficient &lt;inline-formula&gt;&lt;tex-math&gt;$k$&lt;/tex-math&gt;&lt;alternatives&gt; &lt;inline-graphic xlink:type=\"simple\" xlink:href=\"qu-ieq1-2306193.gif\"/&gt;&lt;/alternatives&gt;&lt;/inline-formula&gt;-Means++ Approximation with MapReduce","publication_year":2014,"publication_date":"2014-02-13","ids":{"openalex":"https://openalex.org/W2069564486","doi":"https://doi.org/10.1109/tpds.2014.2306193","mag":"2069564486"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2014.2306193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2306193","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5101916630","display_name":"Yujie Xu","orcid":"https://orcid.org/0000-0002-9302-9579"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yujie Xu","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041346888","display_name":"Wenyu Qu","orcid":"https://orcid.org/0000-0003-4817-5187"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Qu","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730072","display_name":"Zhiyang Li","orcid":"https://orcid.org/0000-0002-5396-3447"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyang Li","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770003","display_name":"Geyong Min","orcid":"https://orcid.org/0000-0003-1395-7314"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]},{"id":"https://openalex.org/I139894009","display_name":"University of Bradford","ror":"https://ror.org/00vs8d940","country_code":"GB","type":"education","lineage":["https://openalex.org/I139894009"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geyong Min","raw_affiliation_strings":["College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, EX4 4QF, United Kingdom","Department of Computing, University of Bradford, West Yorkshire, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, EX4 4QF, United Kingdom","institution_ids":["https://openalex.org/I23923803"]},{"raw_affiliation_string":"Department of Computing, University of Bradford, West Yorkshire, United Kingdom","institution_ids":["https://openalex.org/I139894009"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111982109","display_name":"Keqiu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keqiu Li","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056093982","display_name":"Zhaobin Liu","orcid":"https://orcid.org/0000-0002-3203-6118"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaobin Liu","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101916630"],"corresponding_institution_ids":["https://openalex.org/I43313876"],"apc_list":null,"apc_paid":null,"fwci":11.4841,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.98103179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":"12","first_page":"3135","last_page":"3144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9872000217437744,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/simple","display_name":"Simple (philosophy)","score":0.6061565279960632},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4706261157989502},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.4609343111515045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4596391022205353},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.420685350894928},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3624432384967804}],"concepts":[{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6061565279960632},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4706261157989502},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.4609343111515045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4596391022205353},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.420685350894928},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3624432384967804},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2014.2306193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2306193","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:ore.exeter.ac.uk:10871/20806","is_oa":false,"landing_page_url":"http://hdl.handle.net/10871/20806","pdf_url":null,"source":{"id":"https://openalex.org/S4306401998","display_name":"Open Research Exeter (University of Exeter)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I23923803","host_organization_name":"University of Exeter","host_organization_lineage":["https://openalex.org/I23923803"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G3294051369","display_name":"\u79fb\u52a8\u89c6\u89c9\u68c0\u7d22\u5173\u952e\u6280\u672f\u7684\u7814\u7a76","funder_award_id":"61370199","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3676476879","display_name":null,"funder_award_id":"61300187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4682820497","display_name":"\u9762\u5411\u6d77\u91cf\u56fe\u50cf\u6570\u636e\u7684\u68c0\u7d22\u6280\u672f\u7684\u7814\u7a76","funder_award_id":"61173165","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5054656161","display_name":null,"funder_award_id":"2013QN044","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G699462028","display_name":null,"funder_award_id":"61300189","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7368584553","display_name":"\u4e91\u8ba1\u7b97\u73af\u5883\u4e0b\u52a8\u6001\u591a\u5143\u4fe1\u4efb\u6a21\u578b\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61370198","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G741211149","display_name":null,"funder_award_id":"2012TD008","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7492772654","display_name":"\u4e91\u8ba1\u7b97\u73af\u5883\u4e0b\u6d77\u91cf\u6570\u636e\u67e5\u8be2\u4f18\u5316\u4e0e\u667a\u80fd\u5904\u7406\u7684\u7814\u7a76","funder_award_id":"61173162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1483830423","https://openalex.org/W1976860187","https://openalex.org/W1978489625","https://openalex.org/W1985570011","https://openalex.org/W1990710124","https://openalex.org/W1998325344","https://openalex.org/W2013344760","https://openalex.org/W2026705124","https://openalex.org/W2034616054","https://openalex.org/W2053061798","https://openalex.org/W2059515884","https://openalex.org/W2073459066","https://openalex.org/W2074408893","https://openalex.org/W2079361215","https://openalex.org/W2108399535","https://openalex.org/W2110105238","https://openalex.org/W2111315907","https://openalex.org/W2116762767","https://openalex.org/W2127164716","https://openalex.org/W2150593711","https://openalex.org/W2156499390","https://openalex.org/W2173213060","https://openalex.org/W2199495299","https://openalex.org/W2741690731","https://openalex.org/W4236385439","https://openalex.org/W6628668221","https://openalex.org/W6646687056","https://openalex.org/W6656774490","https://openalex.org/W6668990524","https://openalex.org/W6677347680","https://openalex.org/W6683136438"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2600246793","https://openalex.org/W4238204885"],"abstract_inverted_index":{"k-means":[0],"is":[1,19,32,44,58,117,129,231],"undoubtedly":[2],"one":[3,106],"of":[4,77,99,181,189,206],"the":[5,23,49,62,75,97,120,124,132,143,155,165,178,185,190,220,225],"most":[6],"popular":[7],"clustering":[8],"algorithms":[9],"owing":[10],"to":[11,22,46,53,61,67,109,177],"its":[12,68,82],"simplicity":[13],"and":[14,27,84,123,157,214,219,235],"efficiency.":[15],"However,":[16,65],"this":[17,41,86,136],"algorithm":[18,116,128],"highly":[20],"sensitive":[21],"chosen":[24],"initial":[25],"centers":[26,50],"thus":[28],"a":[29,55,149,196,203,238],"proper":[30],"initialization":[31,115,127],"crucial":[33],"for":[34],"obtaining":[35],"an":[36],"ideal":[37],"solution.":[38],"To":[39,80,183],"address":[40],"problem,":[42],"k-means++":[43,71,91,114,126,140,169,229],"proposed":[45,166,191,226],"sequentially":[47],"choose":[48],"so":[51],"as":[52,74],"achieve":[54,237],"solution":[56,180],"that":[57,164,199,224],"provably":[59],"close":[60],"optimal":[63,179],"one.":[64],"due":[66],"weak":[69],"scalability,":[70],"becomes":[72],"inefficient":[73],"size":[76],"data":[78,216],"increases.":[79],"improve":[81],"scalability":[83],"efficiency,":[85],"paper":[87],"presents":[88],"Map":[89,100,138,167,227],"Reduce":[90,101,139,168,228],"method":[92,141,170,230],"which":[93],"can":[94,153,200,236],"drastically":[95],"reduce":[96,154,184],"number":[98,205],"jobs":[102],"by":[103],"using":[104],"only":[105],"MapReduce":[107],"job":[108],"obtain":[110],"k":[111],"centers.":[112],"The":[113],"executed":[118],"in":[119,131],"Mapper":[121],"phase":[122],"weighted":[125],"run":[130],"Reducer":[133],"phase.":[134],"As":[135],"new":[137],"replaces":[142],"iterations":[144],"among":[145],"multiple":[146],"machines":[147],"with":[148],"single":[150],"machine,":[151],"it":[152],"communication":[156],"I/O":[158],"costs":[159],"significantly.":[160],"We":[161],"also":[162],"prove":[163],"obtains":[171],"O(\u03b1":[172],"<sup":[173],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[174],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[175],")approximation":[176],"k-means.":[182],"expensive":[186],"distance":[187,208],"computation":[188],"method,":[192],"we":[193],"further":[194],"propose":[195],"pruning":[197],"strategy":[198],"greatly":[201],"avoid":[202],"large":[204],"redundant":[207],"computations.":[209],"Extensive":[210],"experiments":[211],"on":[212],"real":[213],"synthetic":[215],"are":[217],"conducted":[218],"performance":[221],"results":[222],"indicate":[223],"much":[232],"more":[233],"efficient":[234],"good":[239],"approximation.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2016-06-24T00:00:00"}
