{"id":"https://openalex.org/W2056512519","doi":"https://doi.org/10.1145/2597917.2597918","title":"A collaborative divide-and-conquer K-means clustering algorithm for processing large data","display_name":"A collaborative divide-and-conquer K-means clustering algorithm for processing large data","publication_year":2014,"publication_date":"2014-05-20","ids":{"openalex":"https://openalex.org/W2056512519","doi":"https://doi.org/10.1145/2597917.2597918","mag":"2056512519"},"language":"en","primary_location":{"id":"doi:10.1145/2597917.2597918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597917.2597918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM Conference on Computing Frontiers","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/A5089123963","display_name":"Huimin Cui","orcid":"https://orcid.org/0009-0006-5884-3985"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huimin Cui","raw_affiliation_strings":["SKL of Computer Architecture, Institute of Computing Technology, CAS, China"],"affiliations":[{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048361599","display_name":"Gong Ruan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong Ruan","raw_affiliation_strings":["University of Chinese Academy of Sciences, China","University of Chinese Academy of Sciences, China;"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China;","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024664385","display_name":"Jingling Xue","orcid":"https://orcid.org/0000-0003-0380-3506"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jingling Xue","raw_affiliation_strings":["University of New South Wales, Australia","Univ. of New South wales, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Univ. of New South wales, Australia#TAB#","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038984205","display_name":"Rui Xie","orcid":"https://orcid.org/0000-0001-9300-7145"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xie","raw_affiliation_strings":["SKL of Computer Architecture, Institute of Computing Technology, CAS, China"],"affiliations":[{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435758","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0001-6909-9561"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["SKL of Computer Architecture, Institute of Computing Technology, CAS, China"],"affiliations":[{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053070701","display_name":"Xiaobing Feng","orcid":"https://orcid.org/0000-0003-2909-7750"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobing Feng","raw_affiliation_strings":["SKL of Computer Architecture, Institute of Computing Technology, CAS, China"],"affiliations":[{"raw_affiliation_string":"SKL of Computer Architecture, Institute of Computing Technology, CAS, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5089123963"],"corresponding_institution_ids":["https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":2.5371,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9106397,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9997000098228455,"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":0.9997000098228455,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9987000226974487,"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":0.9968000054359436,"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":0.8414150476455688},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7444270849227905},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6412396430969238},{"id":"https://openalex.org/keywords/streaming-algorithm","display_name":"Streaming algorithm","score":0.6272683143615723},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6124721765518188},{"id":"https://openalex.org/keywords/divide-and-conquer-algorithms","display_name":"Divide and conquer algorithms","score":0.5973163843154907},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5701737999916077},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5273058414459229},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5131426453590393},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4897022545337677},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44117191433906555},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4214937090873718},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39741551876068115},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3412066102027893},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34054216742515564},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.20169144868850708},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.1905512809753418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18201836943626404},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09339514374732971}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414150476455688},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7444270849227905},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6412396430969238},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.6272683143615723},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6124721765518188},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.5973163843154907},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5701737999916077},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5273058414459229},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5131426453590393},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4897022545337677},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44117191433906555},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4214937090873718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39741551876068115},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3412066102027893},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34054216742515564},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.20169144868850708},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.1905512809753418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18201836943626404},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09339514374732971},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2597917.2597918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597917.2597918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM Conference on Computing Frontiers","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.122","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.unsw.edu.au/%7Ejingling/papers/cf14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[{"id":"https://openalex.org/G1959507677","display_name":null,"funder_award_id":"DP0987236, DP110104628, DP130101970","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G3554421938","display_name":null,"funder_award_id":"2012AA010902","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G3875632391","display_name":null,"funder_award_id":"61202055, 60925009, 61100011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5184694756","display_name":null,"funder_award_id":"2011CB302504","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G7065182657","display_name":null,"funder_award_id":"60921002","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/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W191714665","https://openalex.org/W1498006959","https://openalex.org/W1578468649","https://openalex.org/W1870625491","https://openalex.org/W1963820332","https://openalex.org/W1967368946","https://openalex.org/W1970866964","https://openalex.org/W1973264045","https://openalex.org/W1978394996","https://openalex.org/W1983266860","https://openalex.org/W1998325344","https://openalex.org/W2003207175","https://openalex.org/W2010410498","https://openalex.org/W2011430131","https://openalex.org/W2045964207","https://openalex.org/W2073459066","https://openalex.org/W2091283109","https://openalex.org/W2091684877","https://openalex.org/W2100369465","https://openalex.org/W2108399535","https://openalex.org/W2110105238","https://openalex.org/W2112617148","https://openalex.org/W2116762767","https://openalex.org/W2123297508","https://openalex.org/W2130997333","https://openalex.org/W2143594203","https://openalex.org/W2146756121","https://openalex.org/W2150593711","https://openalex.org/W2156499390","https://openalex.org/W2165612380","https://openalex.org/W2170238528","https://openalex.org/W2199495299","https://openalex.org/W2805677007","https://openalex.org/W3157252607","https://openalex.org/W4236385439","https://openalex.org/W4240165335","https://openalex.org/W4285719527","https://openalex.org/W6629641698","https://openalex.org/W6646263681","https://openalex.org/W6679118781"],"related_works":["https://openalex.org/W2083332996","https://openalex.org/W3009866434","https://openalex.org/W2262713966","https://openalex.org/W2376797789","https://openalex.org/W2898072413","https://openalex.org/W1583949593","https://openalex.org/W2518466227","https://openalex.org/W2746202591","https://openalex.org/W2168667497","https://openalex.org/W3175829541"],"abstract_inverted_index":{"K-means":[0],"clustering":[1,129],"plays":[2],"a":[3,68,85,116],"vital":[4],"role":[5],"in":[6,57],"data":[7,39],"mining.":[8],"As":[9],"an":[10,136,150],"iterative":[11],"computation,":[12],"its":[13,30,128,142],"performance":[14],"will":[15],"suffer":[16],"when":[17],"applied":[18],"to":[19,25,72,88,103,133,147],"tremendous":[20],"amounts":[21],"of":[22,118,138,152],"data,":[23],"due":[24],"poor":[26],"temporal":[27,51],"locality":[28,52],"across":[29],"iterations.":[31],"The":[32],"state-of-the-art":[33],"streaming":[34,113],"algorithm,":[35],"which":[36],"streams":[37],"the":[38,47,75,90,105,112],"from":[40,145],"disk":[41],"into":[42],"memory":[43],"and":[44],"operates":[45],"on":[46,78],"partitioned":[48],"streams,":[49],"improves":[50,127],"but":[53],"can":[54],"misplace":[55],"objects":[56],"clusters":[58,91],"since":[59],"different":[60,101],"partitions":[61,102],"are":[62],"processed":[63],"locally.":[64],"This":[65],"paper":[66],"presents":[67],"collaborative":[69,98,125],"divide-and-conquer":[70],"algorithm":[71,114,126],"significantly":[73],"improve":[74],"state-of-the-art,":[76],"based":[77],"two":[79],"key":[80],"insights.":[81],"First,":[82],"we":[83,96],"introduce":[84,97],"break-and-recluster":[86],"procedure":[87],"identify":[89],"with":[92,111,135,149],"misplaced":[93],"objects.":[94],"Second,":[95],"seeding":[99],"between":[100],"accelerate":[104],"convergence":[106],"inside":[107],"each":[108],"partition.":[109],"Compared":[110],"using":[115],"number":[117],"wikipedia":[119],"webpages":[120],"as":[121],"our":[122,124],"datasets,":[123],"quality":[130],"by":[131],"up":[132],"35.3%":[134],"average":[137,151],"8.8%":[139],"while":[140],"decreasing":[141],"execution":[143],"times":[144],"0.3%":[146],"80.1%":[148],"48.6%.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}