{"id":"https://openalex.org/W2970204018","doi":"https://doi.org/10.14778/3352063.3352128","title":"Customizable and scalable fuzzy join for big data","display_name":"Customizable and scalable fuzzy join for big data","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2970204018","doi":"https://doi.org/10.14778/3352063.3352128","mag":"2970204018"},"language":"en","primary_location":{"id":"doi:10.14778/3352063.3352128","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3352063.3352128","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5100382188","display_name":"Zhimin Chen","orcid":"https://orcid.org/0000-0002-7027-9858"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zhimin Chen","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372034","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-4563-1995"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063257827","display_name":"Vivek Narasayya","orcid":"https://orcid.org/0000-0001-7011-7886"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vivek Narasayya","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038037154","display_name":"Surajit Chaudhuri","orcid":"https://orcid.org/0000-0001-8252-5270"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Surajit Chaudhuri","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100382188"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":1.2372,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81979243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"12","issue":"12","first_page":"2106","last_page":"2117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9905999898910522,"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/computer-science","display_name":"Computer science","score":0.8121830821037292},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7614515423774719},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5728004574775696},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5717875957489014},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.5698084831237793},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4880324900150299},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.45312124490737915},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.43983569741249084},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.43486249446868896},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32171630859375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16427606344223022},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10198593139648438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121830821037292},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7614515423774719},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5728004574775696},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5717875957489014},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.5698084831237793},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4880324900150299},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.45312124490737915},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.43983569741249084},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.43486249446868896},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32171630859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16427606344223022},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10198593139648438},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3352063.3352128","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3352063.3352128","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W1660390307","https://openalex.org/W1997927541","https://openalex.org/W2001700730","https://openalex.org/W2007682403","https://openalex.org/W2055906546","https://openalex.org/W2072173758","https://openalex.org/W2073167797","https://openalex.org/W2093050254","https://openalex.org/W2104599107","https://openalex.org/W2105423800","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2132399973","https://openalex.org/W2137139422","https://openalex.org/W2151930506","https://openalex.org/W2161936973","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2270660075","https://openalex.org/W2294331997","https://openalex.org/W2398657955","https://openalex.org/W2616120155","https://openalex.org/W2883952940","https://openalex.org/W6629956336","https://openalex.org/W6637101025","https://openalex.org/W6674576723","https://openalex.org/W6683401941","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W3214148052","https://openalex.org/W2151692181","https://openalex.org/W794462722","https://openalex.org/W2029625042","https://openalex.org/W4390608645","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991"],"abstract_inverted_index":{"Fuzzy":[0],"join":[1,14,66],"is":[2,15],"an":[3],"important":[4],"primitive":[5],"for":[6,36],"data":[7,23,109,129],"cleaning.":[8],"The":[9],"ability":[10],"to":[11,17,20,117,125],"customize":[12],"fuzzy":[13,41,65],"crucial":[16],"allow":[18],"applications":[19],"address":[21],"domain-specific":[22],"quality":[24],"issues":[25],"such":[26],"as":[27],"synonyms":[28],"and":[29,51,55,79,107,123,131],"abbreviations.":[30],"While":[31],"efficient":[32],"indexing":[33],"techniques":[34,46],"exist":[35],"single-node":[37],"implementations":[38],"of":[39,62,102,133],"customizable":[40],"join,":[42],"the":[43,60,98,118],"state-of-the-art":[44],"scale-out":[45,64,121],"do":[47],"not":[48],"support":[49],"customization,":[50],"exhibit":[52],"poor":[53],"performance":[54],"scalability":[56,127],"characteristics.":[57],"We":[58,71,93,111],"describe":[59],"design":[61],"a":[63,73],"operator":[67],"that":[68,82],"supports":[69],"customization.":[70],"use":[72],"locality-sensitive-hashing":[74],"(LSH)":[75],"based":[76],"signature":[77],"scheme,":[78],"introduce":[80],"optimizations":[81],"result":[83],"in":[84],"significant":[85],"speed":[86],"up":[87],"with":[88,128],"negligible":[89],"impact":[90],"on":[91,97],"recall.":[92],"evaluate":[94],"our":[95],"implementation":[96],"Azure":[99],"Databricks":[100],"version":[101],"Spark":[103],"using":[104],"several":[105],"real-world":[106],"synthetic":[108],"sets.":[110],"observe":[112],"speedups":[113],"exceeding":[114],"50X":[115],"compared":[116],"best-known":[119],"prior":[120],"technique,":[122],"close":[124],"linear":[126],"size":[130],"number":[132],"nodes.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}