{"id":"https://openalex.org/W2555648367","doi":"https://doi.org/10.1109/tkde.2016.2631599","title":"Metric Similarity Joins Using MapReduce","display_name":"Metric Similarity Joins Using MapReduce","publication_year":2016,"publication_date":"2016-11-23","ids":{"openalex":"https://openalex.org/W2555648367","doi":"https://doi.org/10.1109/tkde.2016.2631599","mag":"2555648367"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2016.2631599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2631599","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","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/A5100389222","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0001-7120-7058"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gang Chen","raw_affiliation_strings":["Key Laboratory of Big Data Intelligent Computing of Zhejiang Province, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data Intelligent Computing of Zhejiang Province, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041861486","display_name":"Keyu Yang","orcid":"https://orcid.org/0009-0007-1649-1448"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyu Yang","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432093","display_name":"Lu Chen","orcid":"https://orcid.org/0000-0002-5685-7017"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Chen","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006238145","display_name":"Yunjun Gao","orcid":"https://orcid.org/0000-0003-3816-8450"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjun Gao","raw_affiliation_strings":["Key Laboratory of Big Data Intelligent Computing of Zhejiang Province, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data Intelligent Computing of Zhejiang Province, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050328715","display_name":"Baihua Zheng","orcid":"https://orcid.org/0000-0001-9792-9171"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Baihua Zheng","raw_affiliation_strings":["School of Information Systems, Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100373367","display_name":"Chun Chen","orcid":"https://orcid.org/0000-0002-6198-7481"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Chen","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100389222"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":4.5934,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95680867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"29","issue":"3","first_page":"656","last_page":"669"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9980000257492065,"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":0.9980000257492065,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9957000017166138,"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/T11719","display_name":"Data Quality and Management","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7754085063934326},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7618905305862427},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6062157154083252},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5746667981147766},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5538411140441895},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5385051965713501},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.5364373922348022},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.5178859233856201},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4705890715122223},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4452989101409912},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.41505327820777893},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33778202533721924},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25340062379837036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19544512033462524},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16447597742080688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754085063934326},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7618905305862427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6062157154083252},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5746667981147766},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5538411140441895},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5385051965713501},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.5364373922348022},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.5178859233856201},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4705890715122223},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4452989101409912},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.41505327820777893},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33778202533721924},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25340062379837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19544512033462524},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16447597742080688},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2016.2631599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2631599","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-4325","is_oa":false,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=4325&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TKDE.2016.2631599","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4333703567","display_name":null,"funder_award_id":"61472348","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7048928806","display_name":null,"funder_award_id":"61379033","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8438808684","display_name":null,"funder_award_id":"61522208","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":43,"referenced_works":["https://openalex.org/W11282104","https://openalex.org/W14135646","https://openalex.org/W46452414","https://openalex.org/W182666420","https://openalex.org/W299839057","https://openalex.org/W980041598","https://openalex.org/W1550211845","https://openalex.org/W1568832590","https://openalex.org/W1573493856","https://openalex.org/W1608801065","https://openalex.org/W1870305865","https://openalex.org/W1979666709","https://openalex.org/W1983067644","https://openalex.org/W1992419399","https://openalex.org/W2001700730","https://openalex.org/W2015666340","https://openalex.org/W2035300369","https://openalex.org/W2044936152","https://openalex.org/W2061601738","https://openalex.org/W2068665379","https://openalex.org/W2085713192","https://openalex.org/W2085922539","https://openalex.org/W2097184821","https://openalex.org/W2104599107","https://openalex.org/W2112995410","https://openalex.org/W2115500858","https://openalex.org/W2121516976","https://openalex.org/W2122829408","https://openalex.org/W2151930506","https://openalex.org/W2152565070","https://openalex.org/W2154138844","https://openalex.org/W2164529774","https://openalex.org/W2164634022","https://openalex.org/W2166741129","https://openalex.org/W2169387919","https://openalex.org/W2169795703","https://openalex.org/W2173213060","https://openalex.org/W2182609552","https://openalex.org/W2270660075","https://openalex.org/W4242221949","https://openalex.org/W6600590055","https://openalex.org/W6601892241","https://openalex.org/W6634144655"],"related_works":["https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2016456293","https://openalex.org/W2161128265","https://openalex.org/W1997896902","https://openalex.org/W2138101384","https://openalex.org/W2140894225","https://openalex.org/W2125826941","https://openalex.org/W4212828571","https://openalex.org/W2239248532"],"abstract_inverted_index":{"Given":[0],"two":[1,84,144],"object":[2,13,134,146],"sets":[3,147,177],"Q":[4],"and":[5,31,53,93,105,160,174],"O,":[6],"a":[7,17,23,37,55,65,139],"metric":[8,49,74],"similarity":[9,50,75],"join":[10,51],"finds":[11],"similar":[12],"pairs":[14],"according":[15],"to":[16,34,71,98,111,122],"certain":[18],"criterion.":[19],"This":[20],"operation":[21],"has":[22],"wide":[24],"variety":[25],"of":[26,44],"applications":[27],"in":[28,148],"data":[29,32,45,101,126,176],"cleaning":[30],"mining,":[33],"name":[35],"but":[36],"few.":[38],"However,":[39],"the":[40,79,91,94,100,118,125,128,143,151,154,157,161],"rapidly":[41],"growing":[42],"volume":[43],"nowadays":[46],"challenges":[47],"traditional":[48],"methods,":[52],"thus,":[54],"distributed":[56,67],"method":[57],"is":[58],"required.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,82,137],"adopt":[64],"popular":[66],"framework,":[68],"namely,":[69],"MapReduce,":[70],"support":[72],"scalable":[73],"joins.":[76],"To":[77,131],"ensure":[78],"load":[80],"balancing,":[81],"present":[83],"sampling":[85],"based":[86],"partition":[87],"methods.":[88],"One":[89],"utilizes":[90],"pivot":[92,129,158],"space-filling":[95],"curve":[96],"mappings":[97],"cluster":[99],"into":[102],"one-dimensional":[103],"space,":[104],"then":[106],"selects":[107],"high":[108],"quality":[109],"centroids":[110],"enable":[112],"equal-sized":[113],"partitions.":[114],"The":[115],"other":[116],"uses":[117],"KD-tree":[119],"partitioning":[120],"technique":[121],"equally":[123],"divide":[124],"after":[127],"mapping.":[130],"avoid":[132],"unnecessary":[133],"pair":[135],"evaluation,":[136],"propose":[138],"framework":[140],"that":[141,179],"maps":[142],"involved":[145],"order,":[149],"where":[150],"range-object":[152],"filtering,":[153,156,159],"double-pivot":[155],"plane":[162],"sweeping":[163],"techniques":[164],"are":[165],"utilized":[166],"for":[167],"pruning.":[168],"Extensive":[169],"experiments":[170],"with":[171],"both":[172],"real":[173],"synthetic":[175],"demonstrate":[178],"our":[180],"solutions":[181],"outperform":[182],"significantly":[183],"existing":[184],"state-of-the-art":[185],"competitors.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}