{"id":"https://openalex.org/W2619410666","doi":"https://doi.org/10.14778/3099622.3099624","title":"Leveraging set relations in exact set similarity join","display_name":"Leveraging set relations in exact set similarity join","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2619410666","doi":"https://doi.org/10.14778/3099622.3099624","mag":"2619410666"},"language":"en","primary_location":{"id":"doi:10.14778/3099622.3099624","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3099622.3099624","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":true,"oa_status":"green","oa_url":"https://opus.lib.uts.edu.au/bitstream/10453/127415/1/PVLDB_2017_similarity.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101540780","display_name":"Xubo Wang","orcid":"https://orcid.org/0000-0003-3522-7435"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xubo Wang","raw_affiliation_strings":["University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046220908","display_name":"Lu Qin","orcid":"https://orcid.org/0000-0001-6068-5062"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lu Qin","raw_affiliation_strings":["University of Technology Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659938","display_name":"Xuemin Lin","orcid":"https://orcid.org/0000-0003-2396-7225"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuemin Lin","raw_affiliation_strings":["University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386104","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-2674-1638"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["University of Technology Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037530341","display_name":"Lijun Chang","orcid":"https://orcid.org/0000-0002-6830-3900"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lijun Chang","raw_affiliation_strings":["University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7444,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96838454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":"9","first_page":"925","last_page":"936"},"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":0.998199999332428,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.6675549745559692},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6407133340835571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6124258041381836},{"id":"https://openalex.org/keywords/set-operations","display_name":"Set operations","score":0.5492066740989685},{"id":"https://openalex.org/keywords/set-cover-problem","display_name":"Set cover problem","score":0.5240902304649353},{"id":"https://openalex.org/keywords/power-set","display_name":"Power set","score":0.5059656500816345},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4960874021053314},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4776267409324646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46673664450645447},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4644463360309601},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4589065611362457},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.45534831285476685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32546570897102356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20153793692588806},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.09260410070419312}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.6675549745559692},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6407133340835571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6124258041381836},{"id":"https://openalex.org/C2777168461","wikidata":"https://www.wikidata.org/wiki/Q42196253","display_name":"Set operations","level":3,"score":0.5492066740989685},{"id":"https://openalex.org/C100808899","wikidata":"https://www.wikidata.org/wiki/Q1192100","display_name":"Set cover problem","level":3,"score":0.5240902304649353},{"id":"https://openalex.org/C100643331","wikidata":"https://www.wikidata.org/wiki/Q205170","display_name":"Power set","level":3,"score":0.5059656500816345},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4960874021053314},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4776267409324646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46673664450645447},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4644463360309601},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4589065611362457},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.45534831285476685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32546570897102356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20153793692588806},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.09260410070419312},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/3099622.3099624","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3099622.3099624","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"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/127415","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/127415","pdf_url":"https://opus.lib.uts.edu.au/bitstream/10453/127415/1/PVLDB_2017_similarity.pdf","source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/119586","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/119586","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/123053","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/123053","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:opus.lib.uts.edu.au:10453/127415","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/127415","pdf_url":"https://opus.lib.uts.edu.au/bitstream/10453/127415/1/PVLDB_2017_similarity.pdf","source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G204887131","display_name":null,"funder_award_id":"DP150102728","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2545615073","display_name":null,"funder_award_id":"DP170101628","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4611444012","display_name":null,"funder_award_id":"NSFC61232006","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"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2619410666.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W1526394777","https://openalex.org/W1972972498","https://openalex.org/W1990334093","https://openalex.org/W1991800036","https://openalex.org/W2035835285","https://openalex.org/W2037562342","https://openalex.org/W2038281398","https://openalex.org/W2056748234","https://openalex.org/W2065259291","https://openalex.org/W2093270024","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2098571654","https://openalex.org/W2104599107","https://openalex.org/W2105436061","https://openalex.org/W2109803107","https://openalex.org/W2114353347","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2123427850","https://openalex.org/W2147717514","https://openalex.org/W2151930506","https://openalex.org/W2156855109","https://openalex.org/W2270660075","https://openalex.org/W2294222380","https://openalex.org/W2294331997","https://openalex.org/W2396588571","https://openalex.org/W2575812256","https://openalex.org/W3099795033"],"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/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W1501284171"],"abstract_inverted_index":{"Exact":[0],"set":[1,9,30,69,99,104,153,198,233,242],"similarity":[2,31],"join,":[3],"which":[4,37,71,132,226],"finds":[5],"all":[6,283,288],"the":[7,48,57,80,103,111,123,129,137,142,146,157,164,167,171,185,203,207,229,246,252,284,301],"similar":[8,54,241],"pairs":[10,43,55],"from":[11,234,248,269],"two":[12,211],"collections":[13],"of":[14,24,41,96,122,139,166,231,239,273,297],"sets,":[15],"is":[16,75,126],"a":[17,21,34,39,219,270],"fundamental":[18],"problem":[19],"with":[20,265],"wide":[22,271],"range":[23,272],"applications.":[25],"The":[26,275],"existing":[27,147,285],"solutions":[28],"for":[29,145],"join":[32],"follow":[33],"filtering-verification":[35],"framework,":[36],"generates":[38,228],"list":[40],"candidate":[42],"through":[44,83],"scanning":[45],"indexes":[46],"in":[47,56,92,106,141,184,192],"filtering":[49,130,158,173],"phase,":[50,131],"and":[51,187,290],"reports":[52],"those":[53],"verification":[58],"phase.":[59],"Though":[60],"much":[61],"research":[62],"has":[63,117],"been":[64,89,118],"conducted":[65],"on":[66,78,128,206],"this":[67,93,177],"problem,":[68],"relations,":[70],"we":[72,101,150,195,256],"find":[73],"out":[74],"quite":[76],"effective":[77],"improving":[79],"algorithm":[81,204,225,281],"efficiency":[82],"computational":[84,113,124,253],"cost":[85,159],"sharing,":[86],"have":[87,218],"never":[88],"studied.":[90],"Therefore,":[91],"paper,":[94],"instead":[95],"considering":[97],"each":[98],"individually,":[100],"explore":[102,151,196],"relations":[105,154,199],"different":[107],"levels":[108],"to":[109,136,155,160,163,200,250],"reduce":[110,156,251],"overall":[112],"costs.":[114],"First,":[115],"it":[116],"shown":[119],"that":[120,209,279],"most":[121],"time":[125],"spent":[127],"can":[133,291],"be":[134,161],"quadratic":[135],"number":[138],"sets":[140,181,212],"worst":[143],"case":[144],"solutions.":[148],"Thus":[149],"index-level":[152],"linear":[162],"size":[165],"input":[168],"while":[169],"keeping":[170],"same":[172],"power.":[174],"We":[175,222],"achieve":[176,292],"by":[178],"grouping":[179],"related":[180],"into":[182],"blocks":[183],"index":[186,190],"skipping":[188],"useless":[189],"probes":[191],"joins.":[193],"Second,":[194],"answer-level":[197],"further":[201],"improve":[202],"based":[205],"intuition":[208],"if":[210],"are":[213],"similar,":[214],"their":[215],"answers":[216],"may":[217],"large":[220],"overlap.":[221],"derive":[223],"an":[224,235,295],"incrementally":[227],"answer":[230,238,247],"one":[232],"already":[236],"computed":[237],"another":[240],"rather":[243],"than":[244,294],"compute":[245],"scratch":[249],"cost.":[254],"Finally,":[255],"conduct":[257],"extensive":[258],"performance":[259],"studies":[260],"using":[261],"21":[262],"real":[263],"datasets":[264,289],"various":[266],"data":[267],"properties":[268],"domains.":[274],"experimental":[276],"results":[277],"demonstrate":[278],"our":[280],"outperforms":[282],"algorithms":[286],"across":[287],"more":[293],"order":[296],"magnitude":[298],"speedup":[299],"against":[300],"state-":[302],"of-the-art":[303],"algorithms.":[304]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}