{"id":"https://openalex.org/W4323896842","doi":"https://doi.org/10.1109/tbdata.2023.3255003","title":"Approximate Clustering Ensemble Method for Big Data","display_name":"Approximate Clustering Ensemble Method for Big Data","publication_year":2023,"publication_date":"2023-03-10","ids":{"openalex":"https://openalex.org/W4323896842","doi":"https://doi.org/10.1109/tbdata.2023.3255003"},"language":"en","primary_location":{"id":"doi:10.1109/tbdata.2023.3255003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2023.3255003","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Big Data","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/A5056369956","display_name":"Mohammad Sultan Mahmud","orcid":"https://orcid.org/0000-0002-5795-787X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mohammad Sultan Mahmud","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5795-787X","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003347359","display_name":"Joshua Zhexue Huang","orcid":"https://orcid.org/0000-0002-6797-2571"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Joshua Zhexue Huang","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6797-2571","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014049285","display_name":"Rukhsana Ruby","orcid":"https://orcid.org/0000-0002-8373-9542"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rukhsana Ruby","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8373-9542","affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035666851","display_name":"Alladoumbaye Ngueilbaye","orcid":"https://orcid.org/0000-0002-5853-9354"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Alladoumbaye Ngueilbaye","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5853-9354","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001188748","display_name":"Kaishun Wu","orcid":"https://orcid.org/0000-0003-2216-0737"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaishun Wu","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2216-0737","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056369956"],"corresponding_institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4210099586"],"apc_list":null,"apc_paid":null,"fwci":5.2827,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.96465597,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"9","issue":"4","first_page":"1142","last_page":"1155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","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"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","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/T12761","display_name":"Data Stream Mining Techniques","score":0.9972000122070312,"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":0.9952999949455261,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8010079264640808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7192496061325073},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.5478193759918213},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5455113053321838},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.445995569229126},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4457399249076843},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.42189836502075195},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.41405177116394043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23645392060279846},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2046043872833252},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07813170552253723}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8010079264640808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7192496061325073},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5478193759918213},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5455113053321838},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.445995569229126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4457399249076843},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.42189836502075195},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.41405177116394043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23645392060279846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2046043872833252},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07813170552253723},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2023.3255003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2023.3255003","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Big Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7924544171","display_name":null,"funder_award_id":"61972261","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W30689778","https://openalex.org/W1510497687","https://openalex.org/W1648123822","https://openalex.org/W1967168896","https://openalex.org/W1988764623","https://openalex.org/W1992929897","https://openalex.org/W2051224630","https://openalex.org/W2070232376","https://openalex.org/W2085487226","https://openalex.org/W2094048240","https://openalex.org/W2109337768","https://openalex.org/W2111596024","https://openalex.org/W2115346774","https://openalex.org/W2116984363","https://openalex.org/W2139280638","https://openalex.org/W2144419338","https://openalex.org/W2160200253","https://openalex.org/W2162833336","https://openalex.org/W2165232124","https://openalex.org/W2262682506","https://openalex.org/W2343075025","https://openalex.org/W2576424542","https://openalex.org/W2605029335","https://openalex.org/W2773612851","https://openalex.org/W2776558668","https://openalex.org/W2789456849","https://openalex.org/W2806794445","https://openalex.org/W2807006342","https://openalex.org/W2808726866","https://openalex.org/W2884562637","https://openalex.org/W2890125629","https://openalex.org/W2898836160","https://openalex.org/W2921065608","https://openalex.org/W2950244530","https://openalex.org/W2980011823","https://openalex.org/W3018761215","https://openalex.org/W3048364984","https://openalex.org/W3092037388","https://openalex.org/W3121769020","https://openalex.org/W3130789079","https://openalex.org/W4246274742","https://openalex.org/W4251348903","https://openalex.org/W6684050148"],"related_works":["https://openalex.org/W1999117613","https://openalex.org/W2040929534","https://openalex.org/W3022637481","https://openalex.org/W2393816671","https://openalex.org/W3120229345","https://openalex.org/W2111119584","https://openalex.org/W3144143113","https://openalex.org/W3039964395","https://openalex.org/W2804957450","https://openalex.org/W2357208913"],"abstract_inverted_index":{"Clustering":[0],"a":[1,11,27,57,84,96,113,123,144,204,218],"big":[2,32,80,97,313],"distributed":[3,15,85,114,304],"dataset":[4,33,98,272],"of":[5,30,42,55,74,78,125,143,220,238,255],"hundred":[6],"gigabytes":[7],"or":[8],"more":[9],"is":[10,24,99,129,224,230,307],"challenging":[12],"task":[13],"in":[14,101,112,138,311],"computing.":[16],"A":[17,226],"popular":[18],"method":[19,197,229,245,249],"to":[20,25,34,66,88,146,157,184,202,210,233,250,268],"tackle":[21],"this":[22,52,94],"problem":[23],"use":[26,62],"random":[28,59,64,107,133,168],"sample":[29,108],"the":[31,43,48,72,75,79,90,102,119,141,148,158,163,167,186,191,207,212,235,247,252,261,270,290,298,303],"compute":[35,67,89,118],"an":[36,40,68],"approximate":[37],"result":[38,45,70,77],"as":[39,71,106,132],"estimation":[41,73],"true":[44,76],"computed":[46],"from":[47,216],"entire":[49,271],"dataset.":[50,81],"In":[51,93],"paper,":[53],"instead":[54],"using":[56],"single":[58],"sample,":[60],"we":[61,179],"multiple":[63],"samples":[65,134,169],"ensemble":[69,91,120,164,193,292],"We":[82],"propose":[83,180],"computing":[86,305],"framework":[87,306],"result.":[92,165,194],"framework,":[95],"represented":[100],"RSP":[103,126],"data":[104,109,127],"model":[105],"blocks":[110,128],"managed":[111],"file":[115],"system.":[116],"To":[117],"clustering":[121,150,188,228,293,312],"result,":[122],"set":[124,219,237,254],"randomly":[130],"selected":[131],"and":[135,172,206,283,301,309],"clustered":[136],"independently":[137],"parallel":[139],"on":[140,280],"nodes":[142],"cluster":[145,200,222,241,258],"generate":[147,234,251],"component":[149,153,187,199],"results.":[151],"The":[152,195,243,286],"results":[154,189,287],"are":[155,170],"transferred":[156],"master":[159],"node,":[160],"which":[161,217],"computes":[162],"Since":[166],"disjoint":[171],"traditional":[173],"consensus":[174],"functions":[175],"cannot":[176],"be":[177],"used,":[178],"two":[181],"new":[182,291],"methods":[183,294,300],"integrate":[185],"into":[190,214,273],"final":[192,236,253],"first":[196],"uses":[198,246],"centers":[201,223],"build":[203],"graph":[205,213],"METIS":[208],"algorithm":[209,265],"cut":[211],"subgraphs,":[215],"candidate":[221],"found.":[225],"hierarchical":[227],"then":[231],"used":[232,267],"<inline-formula><tex-math":[239,256,262,274],"notation=\"LaTeX\">$k$</tex-math></inline-formula>":[240,257,263,275],"centers.":[242,259],"second":[244],"clustering-by-passing-messages":[248],"Finally,":[260],"-means":[264],"was":[266],"allocate":[269],"clusters.":[276],"Experiments":[277],"were":[278],"conducted":[279],"both":[281],"synthetic":[282],"real-world":[284],"datasets.":[285,314],"show":[288],"that":[289,302],"performed":[295],"better":[296],"than":[297],"comparison":[299],"efficient":[308],"scalable":[310]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}