{"id":"https://openalex.org/W2093050254","doi":"https://doi.org/10.1145/2213836.2213935","title":"Exploiting MapReduce-based similarity joins","display_name":"Exploiting MapReduce-based similarity joins","publication_year":2012,"publication_date":"2012-05-20","ids":{"openalex":"https://openalex.org/W2093050254","doi":"https://doi.org/10.1145/2213836.2213935","mag":"2093050254"},"language":"en","primary_location":{"id":"doi:10.1145/2213836.2213935","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213836.2213935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data","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/A5088912009","display_name":"Yasin N. Silva","orcid":"https://orcid.org/0000-0003-1852-1683"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasin N. Silva","raw_affiliation_strings":["Arizona State University, Glendale, AZ, USA","Arizona State University , Glendale, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Glendale, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University , Glendale, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065710004","display_name":"Jason M. Reed","orcid":"https://orcid.org/0009-0009-9738-404X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason M. Reed","raw_affiliation_strings":["Arizona State University, Glendale, AZ, USA","Arizona State University , Glendale, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Glendale, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University , Glendale, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7153,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.95174856,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"693","last_page":"696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994999766349792,"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":0.9994999766349792,"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/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/joins","display_name":"Joins","score":0.8956685066223145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8332206010818481},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6535630226135254},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6530517339706421},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6003002524375916},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5483865141868591},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4680499732494354},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.453946590423584},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37516552209854126},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3626938462257385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11516228318214417}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8956685066223145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332206010818481},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6535630226135254},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6530517339706421},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6003002524375916},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5483865141868591},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4680499732494354},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.453946590423584},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37516552209854126},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3626938462257385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11516228318214417},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2213836.2213935","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213836.2213935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.941.2858","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.941.2858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.public.asu.edu/%7Eynsilva/publications/ExploitingMRSimJoin.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1573493856","https://openalex.org/W2065528935","https://openalex.org/W2115500858","https://openalex.org/W2121516976","https://openalex.org/W2128793454","https://openalex.org/W2151930506","https://openalex.org/W2154894831","https://openalex.org/W2173213060","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2393491644","https://openalex.org/W2067184662","https://openalex.org/W3047837489","https://openalex.org/W2622139626","https://openalex.org/W2133660117","https://openalex.org/W2104496206","https://openalex.org/W2892165056","https://openalex.org/W2098964748"],"abstract_inverted_index":{"Cloud":[0,212],"enabled":[1],"systems":[2],"have":[3,51,124],"become":[4],"a":[5,40,74,103,129,175],"crucial":[6],"component":[7],"to":[8,79,99,112,163],"efficiently":[9,80,87],"process":[10],"and":[11,23,48,89,153,171,194],"analyze":[12],"massive":[13],"amounts":[14],"of":[15,18,64,161,196,204],"data.":[16],"One":[17],"the":[19,27,62,82,91,94,159,202],"key":[20],"data":[21,33,92,116,146,151,192],"processing":[22],"analysis":[24,147],"operations":[25],"is":[26,109],"Similarity":[28,55,65,83],"Join,":[29],"which":[30],"retrieves":[31],"all":[32],"pairs":[34],"whose":[35],"distances":[36],"are":[37,96],"smaller":[38],"than":[39],"pre-defined":[41],"threshold":[42],"\u2208.":[43],"Even":[44],"though":[45],"multiple":[46,144,150],"algorithms":[47],"implementation":[49],"techniques":[50],"been":[52],"proposed":[53,107],"for":[54,67],"Joins,":[56],"very":[57],"little":[58],"work":[59],"has":[60],"addressed":[61],"study":[63],"Joins":[66],"cloud":[68,133],"systems.":[69],"This":[70],"paper":[71],"presents":[72],"MRSimJoin,":[73],"multi-round":[75],"MapReduce":[76],"based":[77],"algorithm":[78,108],"solve":[81],"Join":[84],"problem.":[85],"MRSimJoin":[86,126,162,182,205],"partitions":[88],"distributes":[90],"until":[93],"subsets":[95],"small":[97],"enough":[98,111],"be":[100,113,141],"processed":[101],"in":[102,119,127,143,174,184],"single":[104],"node.":[105],"The":[106],"general":[110],"used":[114,131,142],"with":[115,149],"that":[117],"lies":[118],"any":[120],"metric":[121],"space.":[122],"We":[123,135,178,200],"implemented":[125],"Hadoop,":[128],"highly":[130],"open-source":[132],"system.":[134],"show":[136,158,180],"how":[137,181],"this":[138],"operation":[139],"can":[140],"real-world":[145],"scenarios":[148],"types":[152],"distance":[154],"functions.":[155],"Particularly,":[156],"we":[157],"use":[160],"identify":[164],"similar":[165,172],"images":[166],"represented":[167],"as":[168],"feature":[169],"vectors,":[170],"publications":[173],"bibliographic":[176],"database.":[177],"also":[179],"scales":[183],"each":[185],"scenario":[186],"when":[187],"important":[188],"parameters,":[189],"e.g.,":[190],"\u2208,":[191],"size":[193],"number":[195],"cluster":[197],"nodes,":[198],"increase.":[199],"demonstrate":[201],"execution":[203],"queries":[206],"using":[207],"an":[208],"Amazon":[209],"Elastic":[210],"Compute":[211],"(EC2)":[213],"cluster.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}