{"id":"https://openalex.org/W2127675794","doi":"https://doi.org/10.1145/1007568.1007652","title":"Efficient set joins on similarity predicates","display_name":"Efficient set joins on similarity predicates","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2127675794","doi":"https://doi.org/10.1145/1007568.1007652","mag":"2127675794"},"language":"en","primary_location":{"id":"doi:10.1145/1007568.1007652","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 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/A5031035935","display_name":"Sunita Sarawagi","orcid":"https://orcid.org/0009-0005-9538-6616"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sunita Sarawagi","raw_affiliation_strings":["IIT Bombay","IIT-Bombay"],"affiliations":[{"raw_affiliation_string":"IIT Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"IIT-Bombay","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064186354","display_name":"Alok Kirpal","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Alok Kirpal","raw_affiliation_strings":["IIT Bombay","IIT-Bombay"],"affiliations":[{"raw_affiliation_string":"IIT Bombay","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"IIT-Bombay","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031035935"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":7.0106,"has_fulltext":false,"cited_by_count":326,"citation_normalized_percentile":{"value":0.97605436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"743","last_page":"754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"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":0.7545483112335205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423912286758423},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.7373992204666138},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.6042084693908691},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5833044052124023},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5277624130249023},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5191401839256287},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4759863615036011},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4617941379547119},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4426579177379608},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.4117531180381775},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4076995253562927},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3614770174026489},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.3554304838180542},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.19198161363601685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15731048583984375},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13213008642196655}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7545483112335205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423912286758423},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.7373992204666138},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.6042084693908691},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5833044052124023},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5277624130249023},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5191401839256287},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4759863615036011},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4617941379547119},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4426579177379608},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.4117531180381775},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4076995253562927},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3614770174026489},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3554304838180542},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.19198161363601685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15731048583984375},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13213008642196655},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1007568.1007652","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W32997993","https://openalex.org/W191231183","https://openalex.org/W1484413656","https://openalex.org/W1500547548","https://openalex.org/W1506285740","https://openalex.org/W1559390933","https://openalex.org/W1612155886","https://openalex.org/W1768336749","https://openalex.org/W1984629602","https://openalex.org/W2010454887","https://openalex.org/W2048779798","https://openalex.org/W2052581258","https://openalex.org/W2067566391","https://openalex.org/W2105423800","https://openalex.org/W2115482638","https://openalex.org/W2132069633","https://openalex.org/W2140795521","https://openalex.org/W2141469207","https://openalex.org/W2150698190","https://openalex.org/W2152401660","https://openalex.org/W2152565070","https://openalex.org/W2160484851","https://openalex.org/W2161936973","https://openalex.org/W2172096705","https://openalex.org/W2251699075","https://openalex.org/W2608151934","https://openalex.org/W2621280964","https://openalex.org/W6629856530","https://openalex.org/W6638104246","https://openalex.org/W6652760581"],"related_works":["https://openalex.org/W2775696757","https://openalex.org/W4381948805","https://openalex.org/W4214483597","https://openalex.org/W4220978606","https://openalex.org/W4386026606","https://openalex.org/W4220894110","https://openalex.org/W4388145912","https://openalex.org/W2565034015","https://openalex.org/W1437580529","https://openalex.org/W2307895033"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"an":[5,92],"efficient,":[6],"scalable":[7],"and":[8,27,47,60,114],"general":[9],"algorithm":[10,80,109],"for":[11,36],"performing":[12],"set":[13,37,44],"joins":[14,38],"on":[15,39],"predicates":[16,41],"involving":[17],"various":[18],"similarity":[19],"measures":[20,116],"like":[21],"intersect":[22],"size,":[23],"Jaccard-coefficient,":[24],"cosine":[25],"similarity,":[26],"edit-distance.":[28],"This":[29],"expands":[30],"the":[31],"existing":[32],"suite":[33],"of":[34,64,73,101,117],"algorithms":[35],"simpler":[40],"such":[42],"as,":[43],"containment,":[45],"equality":[46],"non-zero":[48],"overlap.":[49],"We":[50],"start":[51],"with":[52,91],"a":[53,62,83],"basic":[54],"inverted":[55],"index":[56,93],"based":[57],"probing":[58],"method":[59],"add":[61],"sequence":[63],"optimizations":[65,105],"that":[66,87],"result":[67],"in":[68,76,82,97,107],"one":[69],"to":[70,95,111],"two":[71],"orders":[72],"magnitude":[74],"improvement":[75],"running":[77],"time.":[78],"The":[79,104],"folds":[81],"data":[84],"partitioning":[85],"strategy":[86],"can":[88],"work":[89],"efficiently":[90],"compressed":[94],"fit":[96],"any":[98],"available":[99],"amount":[100],"main":[102],"memory.":[103],"used":[106],"our":[108],"generalize":[110],"several":[112],"weighted":[113],"unweighted":[115],"partial":[118],"word":[119],"overlap":[120],"between":[121],"sets.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":27},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":29},{"year":2012,"cited_by_count":24}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}