{"id":"https://openalex.org/W2026705124","doi":"https://doi.org/10.1145/2020408.2020516","title":"Clustering very large multi-dimensional datasets with MapReduce","display_name":"Clustering very large multi-dimensional datasets with MapReduce","publication_year":2011,"publication_date":"2011-08-21","ids":{"openalex":"https://openalex.org/W2026705124","doi":"https://doi.org/10.1145/2020408.2020516","mag":"2026705124"},"language":"en","primary_location":{"id":"doi:10.1145/2020408.2020516","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085964688","display_name":"Robson L. F. Cordeiro","orcid":"https://orcid.org/0000-0002-6795-3004"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Robson Leonardo Ferreira Cordeiro","raw_affiliation_strings":["University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020611078","display_name":"Caetano Traina","orcid":"https://orcid.org/0000-0002-6625-6047"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Caetano Traina","raw_affiliation_strings":["University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014783020","display_name":"Agma J. M. Traina","orcid":"https://orcid.org/0000-0003-4929-7258"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Agma Juci Machado Traina","raw_affiliation_strings":["University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031910124","display_name":"Julio L\u00f3pez","orcid":"https://orcid.org/0000-0001-9138-5302"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julio L\u00f3pez","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074561505","display_name":"U Kang","orcid":"https://orcid.org/0000-0002-8774-6950"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"U. Kang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035605036","display_name":"Christos Faloutsos","orcid":"https://orcid.org/0000-0003-2996-9790"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christos Faloutsos","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.0751,"has_fulltext":false,"cited_by_count":152,"citation_normalized_percentile":{"value":0.99585334,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"690","last_page":"698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9962000250816345,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9904000163078308,"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/computer-science","display_name":"Computer science","score":0.8449783325195312},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8128517866134644},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6807022094726562},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.5990889072418213},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5564567446708679},{"id":"https://openalex.org/keywords/subroutine","display_name":"Subroutine","score":0.5474721193313599},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.4899227023124695},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.42819347977638245},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4132521450519562},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.3852190673351288},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.371156245470047},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3429015278816223},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27419304847717285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18046391010284424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8449783325195312},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8128517866134644},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6807022094726562},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.5990889072418213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5564567446708679},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.5474721193313599},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.4899227023124695},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.42819347977638245},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4132521450519562},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.3852190673351288},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.371156245470047},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3429015278816223},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27419304847717285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18046391010284424},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2020408.2020516","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.417.5086","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.417.5086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~christos/PUBLICATIONS/kdd2011_clustering_MR.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W91199005","https://openalex.org/W1967838552","https://openalex.org/W1977496278","https://openalex.org/W1997728726","https://openalex.org/W2065811242","https://openalex.org/W2067877017","https://openalex.org/W2073825221","https://openalex.org/W2079361215","https://openalex.org/W2089055054","https://openalex.org/W2093100781","https://openalex.org/W2103696938","https://openalex.org/W2109130989","https://openalex.org/W2118858274","https://openalex.org/W2126642639","https://openalex.org/W2161284614","https://openalex.org/W2167927436","https://openalex.org/W2168143534","https://openalex.org/W2173213060","https://openalex.org/W3003734944"],"related_works":["https://openalex.org/W2163563073","https://openalex.org/W3186815950","https://openalex.org/W4301002638","https://openalex.org/W2387841221","https://openalex.org/W2371010743","https://openalex.org/W2606552659","https://openalex.org/W2181519036","https://openalex.org/W4253632195","https://openalex.org/W3088133960","https://openalex.org/W2047852079"],"abstract_inverted_index":{"Given":[0],"a":[1,20,25,79,99,140,155],"very":[2,156],"large":[3],"moderate-to-high":[4],"dimensionality":[5],"dataset,":[6],"how":[7,46,65],"could":[8],"one":[9],"cluster":[10],"its":[11,113],"points?":[12],"For":[13],"datasets":[14],"that":[15,92,125],"don't":[16],"fit":[17],"even":[18],"on":[19,61,192],"single":[21],"disk,":[22],"parallelism":[23],"is":[24,217],"first":[26],"class":[27],"option.":[28],"In":[29],"this":[30,37],"paper":[31],"we":[32,82],"explore":[33],"MapReduce":[34],"for":[35,148],"clustering":[36,137,142,175,228],"kind":[38],"of":[39,75,86,177,199,211,233],"data.":[40],"The":[41],"main":[42,103],"questions":[43],"are":[44],"(a)":[45],"to":[47,66,168,203,241],"minimize":[48,67],"the":[49,55,68,84,95,119,146,160,174,178,209,218,225],"I/O":[50],"cost,":[51],"taking":[52],"into":[53],"account":[54],"already":[56],"existing":[57],"data":[58,196],"partition":[59],"(e.g.,":[60],"disks),":[62],"and":[63,97,110,151,181,186,194],"(b)":[64],"network":[69,152],"cost":[70,114,147],"among":[71],"processing":[72],"nodes.":[73],"Either":[74],"them":[76],"may":[77],"be":[78,242],"bottleneck.":[80],"Thus,":[81],"propose":[83,108],"Best":[85],"both":[87],"Worlds":[88],"--":[89],"BoW":[90,109,126],"method,":[91],"automatically":[93],"spots":[94],"bottleneck":[96],"chooses":[98],"good":[100,157],"strategy.":[101],"Our":[102],"contributions":[104],"are:":[105],"(1)":[106],"We":[107,123,189],"carefully":[111],"derive":[112],"functions,":[115],"which":[116],"dynamically":[117],"choose":[118],"best":[120,210],"strategy;":[121],"(2)":[122],"show":[124],"has":[127,183],"numerous":[128],"desirable":[129],"features:":[130],"it":[131,144,162,172,182,236],"can":[132],"work":[133],"with":[134,197],"most":[135],"serial":[136,179],"methods":[138],"as":[139],"plugged-in":[141],"subroutine,":[143],"balances":[145],"disk":[149],"accesses":[150],"accesses,":[153],"achieving":[154],"tradeoff":[158],"between":[159],"two,":[161],"uses":[163],"no":[164],"user-defined":[165],"parameters":[166],"(thanks":[167],"our":[169,212,214],"reasonable":[170],"defaults),":[171],"matches":[173],"quality":[176],"algorithm,":[180],"near-linear":[184],"scale-up;":[185],"finally,":[187],"(3)":[188],"report":[190],"experiments":[191],"real":[193,220],"synthetic":[195],"billions":[198],"points,":[200],"using":[201,244],"up":[202],"1,024":[204],"cores":[205],"in":[206,224],"parallel.":[207],"To":[208],"knowledge,":[213],"Yahoo!":[215],"web":[216],"largest":[219],"dataset":[221],"ever":[222],"reported":[223],"database":[226],"subspace":[227],"literature.":[229],"Spanning":[230],"0.2":[231],"TB":[232],"multi-dimensional":[234],"data,":[235],"took":[237],"only":[238],"8":[239],"minutes":[240],"clustered,":[243],"128":[245],"cores.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":22},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":30},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":15}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}