{"id":"https://openalex.org/W2128793454","doi":"https://doi.org/10.1109/icde.2010.5447873","title":"The similarity join database operator","display_name":"The similarity join database operator","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2128793454","doi":"https://doi.org/10.1109/icde.2010.5447873","mag":"2128793454"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasin N. Silva","raw_affiliation_strings":["Department of Computer Science, Purdue University, IA, USA","Department of Computer Science, Purdue University, Indiana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Purdue University, IA, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, Purdue University, Indiana, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000123743","display_name":"Walid G. Aref","orcid":"https://orcid.org/0000-0001-8169-7775"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Walid G. Aref","raw_affiliation_strings":["Department of Computer Science, Purdue University, IA, USA","Department of Computer Science, Purdue University, Indiana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Purdue University, IA, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, Purdue University, Indiana, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103350899","display_name":"Mohamed H. Ali","orcid":"https://orcid.org/0009-0000-2054-8434"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed H. Ali","raw_affiliation_strings":["Microsoft Corporation, WA, USA","Microsoft Corporation, Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Washington, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.8044,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.9839263,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"892","last_page":"903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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":0.998199999332428,"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":0.8854449987411499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7800886631011963},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6745485067367554},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6116647124290466},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5573340654373169},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.5044559240341187},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.47289764881134033},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.43329542875289917},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4189666509628296},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37522321939468384},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3583980202674866},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15083041787147522},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12337654829025269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11165612936019897}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8854449987411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800886631011963},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6745485067367554},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6116647124290466},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5573340654373169},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.5044559240341187},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.47289764881134033},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.43329542875289917},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4189666509628296},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37522321939468384},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3583980202674866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15083041787147522},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12337654829025269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11165612936019897},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"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/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2010.5447873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"},{"id":"pmh:oai:docs.lib.purdue.edu:ccpubs-1032","is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/ccpubs/15","pdf_url":null,"source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cyber Center Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W57699484","https://openalex.org/W96772584","https://openalex.org/W1500547548","https://openalex.org/W1573493856","https://openalex.org/W1608801065","https://openalex.org/W1761301028","https://openalex.org/W1974995373","https://openalex.org/W2009036829","https://openalex.org/W2016854254","https://openalex.org/W2026815233","https://openalex.org/W2029284999","https://openalex.org/W2045848492","https://openalex.org/W2045921448","https://openalex.org/W2058458206","https://openalex.org/W2076338409","https://openalex.org/W2097184821","https://openalex.org/W2100344784","https://openalex.org/W2115500858","https://openalex.org/W2121516976","https://openalex.org/W2123020735","https://openalex.org/W2123060058","https://openalex.org/W2124645273","https://openalex.org/W2126777999","https://openalex.org/W2132151704","https://openalex.org/W2137037647","https://openalex.org/W2142669732","https://openalex.org/W2150916025","https://openalex.org/W2161936973","https://openalex.org/W2163794926","https://openalex.org/W2166364787","https://openalex.org/W2205071250","https://openalex.org/W2341744633","https://openalex.org/W3016712336","https://openalex.org/W4251805162","https://openalex.org/W6602366985","https://openalex.org/W6629856530","https://openalex.org/W6634144655","https://openalex.org/W6637898976","https://openalex.org/W6679747670","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W650102067","https://openalex.org/W3086237447","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W2622139626","https://openalex.org/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794"],"abstract_inverted_index":{"Similarity":[0],"joins":[1,76,91],"have":[2,34,176],"been":[3,35,66],"studied":[4],"as":[5,77,92,160],"key":[6],"operations":[7],"in":[8,171],"multiple":[9,129],"application":[10],"domains,":[11],"e.g.,":[12],"record":[13],"linkage,":[14],"data":[15,48],"cleaning,":[16],"multimedia":[17],"and":[18,21,31,45,72,105,118,158,180],"video":[19],"applications,":[20],"phenomena":[22],"detection":[23],"on":[24,69,86],"sensor":[25],"networks.":[26],"Multiple":[27],"similarity":[28,60,75,90,102,134,142,154],"join":[29,103,155],"algorithms":[30],"implementation":[32,73,151],"techniques":[33,50],"proposed.":[36],"They":[37],"range":[38],"from":[39],"out-of-database":[40],"approaches":[41],"for":[42,222],"only":[43,201,253],"in-memory":[44],"external":[46],"memory":[47],"to":[49,58,210,230,255],"that":[51,132,174,199,240,251],"make":[52],"use":[53],"of":[54,74,89,100,140,152,167,186,192,195,212,215,226,232,257,260],"standard":[55,115],"database":[56,78,94,116],"operators":[57,104,170,203,219],"answer":[59],"joins.":[61],"Unfortunately,":[62],"there":[63],"has":[64],"not":[65],"much":[67],"study":[68,88,106],"the":[70,87,98,107,138,168,193,196,213,223,233,241,258,261],"role":[71],"physical":[79],"operators.":[80,95,124,163],"In":[81,125],"this":[82],"paper,":[83],"we":[84,127],"focus":[85],"first-class":[93],"We":[96,146,236],"present":[97,128],"definition":[99],"several":[101],"way":[108],"they":[109,175],"interact":[110],"among":[111],"themselves,":[112],"with":[113,119,248],"other":[114,120],"operators,":[117,156],"previously":[121],"proposed":[122,242],"similarity-aware":[123],"particular,":[126],"transformation":[130,243],"rules":[131,244],"enable":[133],"query":[135,143,198,221,263],"optimization":[136],"through":[137],"generation":[139],"equivalent":[141,197,217],"execution":[144,178,184,206,249],"plans.":[145,264],"then":[147],"describe":[148],"an":[149],"efficient":[150],"two":[153],"\u00bf-Join":[157],"Join-Around,":[159],"core":[161],"DBMS":[162],"The":[164,183],"performance":[165],"evaluation":[166],"implemented":[169],"PostgreSQL":[172],"shows":[173],"good":[177],"time":[179,185,207],"scalability":[181],"properties.":[182],"Join-Around":[187],"is":[188,208],"less":[189],"than":[190],"5%":[191],"one":[194,214],"uses":[200],"regular":[202,218],"while":[204],"\u00bf-Join's":[205],"20":[209],"90%":[211],"its":[216],"based":[220],"useful":[224],"case":[225],"small":[227],"\u00bf":[228],"(0.01%":[229],"10%":[231,254],"domain":[234],"range).":[235],"also":[237],"show":[238],"experimentally":[239],"can":[245],"generate":[246],"plans":[247],"times":[250],"are":[252],"70%":[256],"ones":[259],"initial":[262]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":14}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}