{"id":"https://openalex.org/W4319655010","doi":"https://doi.org/10.14778/3574245.3574263","title":"TokenJoin","display_name":"TokenJoin","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4319655010","doi":"https://doi.org/10.14778/3574245.3574263"},"language":"en","primary_location":{"id":"doi:10.14778/3574245.3574263","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3574245.3574263","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://pure.tue.nl/ws/files/299333544/3574245.3574263.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050605929","display_name":"Alexandros Zeakis","orcid":"https://orcid.org/0000-0001-5336-8157"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Alexandros Zeakis","raw_affiliation_strings":["National and Kapodistrian University of Athens & \"Athena\" RC, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National and Kapodistrian University of Athens & \"Athena\" RC, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087768208","display_name":"Dimitrios Skoutas","orcid":"https://orcid.org/0000-0002-6118-5227"},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Skoutas","raw_affiliation_strings":["\"Athena\" RC, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\"Athena\" RC, Greece","institution_ids":["https://openalex.org/I4210156054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090860653","display_name":"Dimitris Sacharidis","orcid":"https://orcid.org/0000-0001-5022-1483"},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dimitris Sacharidis","raw_affiliation_strings":["Universit\u00e9 Libre de Bruxelles, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Libre de Bruxelles, Belgium","institution_ids":["https://openalex.org/I132053463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074684566","display_name":"Odysseas Papapetrou","orcid":"https://orcid.org/0000-0003-0045-1648"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odysseas Papapetrou","raw_affiliation_strings":["Eindhoven University of Technology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075117735","display_name":"Manolis Koubarakis","orcid":"https://orcid.org/0000-0002-1954-8338"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Manolis Koubarakis","raw_affiliation_strings":["National and Kapodistrian University of Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National and Kapodistrian University of Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9023,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76377862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"16","issue":"4","first_page":"790","last_page":"802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980999827384949,"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":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.8763895034790039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.657279372215271},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6312798261642456},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6247950792312622},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.5519996881484985},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5380695462226868},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5328776240348816},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5089664459228516},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.4822733998298645},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46790844202041626},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45751872658729553},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3598908483982086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3519465923309326},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3280075192451477}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8763895034790039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.657279372215271},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6312798261642456},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6247950792312622},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.5519996881484985},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5380695462226868},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5328776240348816},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5089664459228516},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.4822733998298645},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46790844202041626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45751872658729553},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3598908483982086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3519465923309326},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3280075192451477},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/3574245.3574263","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3574245.3574263","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:pure.tue.nl:openaire_cris_publications/a5fe5c44-cb1f-4bf1-a1d3-4b661ae949a7","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/a5fe5c44-cb1f-4bf1-a1d3-4b661ae949a7","pdf_url":"https://pure.tue.nl/ws/files/299333544/3574245.3574263.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zeakis, A, Skoutas, D, Sacharidis, D, Papapetrou, O & Koubarakis, M 2022, 'TokenJoin : Efficient Filtering for Set Similarity Join with MaximumWeighted Bipartite Matching', Proceedings of the VLDB Endowment, vol. 16, no. 4, pp. 790-802. https://doi.org/10.14778/3574245.3574263","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:zenodo.org:7625991","is_oa":true,"landing_page_url":"https://zenodo.org/record/7625991","pdf_url":"https://zenodo.org/record/7625991","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the VLDB Endowment 16(4) 790--802","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:tue:oai:pure.tue.nl:publications/a5fe5c44-cb1f-4bf1-a1d3-4b661ae949a7","is_oa":true,"landing_page_url":"https://research.tue.nl/nl/publications/a5fe5c44-cb1f-4bf1-a1d3-4b661ae949a7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the VLDB Endowment, 16(4), 790 - 802. Very Large Data Base Endowment Inc.","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/a5fe5c44-cb1f-4bf1-a1d3-4b661ae949a7","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/a5fe5c44-cb1f-4bf1-a1d3-4b661ae949a7","pdf_url":"https://pure.tue.nl/ws/files/299333544/3574245.3574263.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zeakis, A, Skoutas, D, Sacharidis, D, Papapetrou, O & Koubarakis, M 2022, 'TokenJoin : Efficient Filtering for Set Similarity Join with MaximumWeighted Bipartite Matching', Proceedings of the VLDB Endowment, vol. 16, no. 4, pp. 790-802. https://doi.org/10.14778/3574245.3574263","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319655010.pdf","grobid_xml":"https://content.openalex.org/works/W4319655010.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1987562803","https://openalex.org/W2019412213","https://openalex.org/W2035835285","https://openalex.org/W2037562342","https://openalex.org/W2050653561","https://openalex.org/W2065259291","https://openalex.org/W2080090262","https://openalex.org/W2093270024","https://openalex.org/W2097776316","https://openalex.org/W2105436061","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2141461755","https://openalex.org/W2150916025","https://openalex.org/W2156279557","https://openalex.org/W2156855109","https://openalex.org/W2166400748","https://openalex.org/W2286724461","https://openalex.org/W2396588571","https://openalex.org/W2606791715","https://openalex.org/W2615658008","https://openalex.org/W2619410666","https://openalex.org/W2883952940","https://openalex.org/W2951438725","https://openalex.org/W2963886823"],"related_works":["https://openalex.org/W1994775821","https://openalex.org/W2775696757","https://openalex.org/W2012019886","https://openalex.org/W2091133150","https://openalex.org/W2945869148","https://openalex.org/W2398781203","https://openalex.org/W2009279505","https://openalex.org/W4206503171","https://openalex.org/W4366711670","https://openalex.org/W2558988915"],"abstract_inverted_index":{"Set":[0],"similarity":[1,21,25,60,96,146],"join":[2,22],"is":[3,118],"an":[4,178],"important":[5,74],"problem":[6],"with":[7],"many":[8],"applications":[9],"in":[10],"data":[11],"discovery,":[12],"cleaning":[13],"and":[14,79],"integration.":[15],"To":[16],"increase":[17],"robustness,":[18],"fuzzy":[19],"set":[20,37],"calculates":[23],"the":[24,68,75,85,133,138,141,155,172,175],"of":[26,36,42,87,100,112,137,157,174,180],"two":[27],"sets":[28,46],"based":[29,57],"on":[30,58,95,162,183],"maximum":[31],"weighted":[32],"bipartite":[33],"matching":[34],"instead":[35,111],"overlap.":[38],"This":[39],"allows":[40],"pairs":[41,99],"elements,":[43],"represented":[44],"as":[45],"or":[47,61,125],"strings,":[48],"to":[49,83,102,153],"also":[50,149],"match":[51],"approximately":[52],"rather":[53],"than":[54],"exactly,":[55],"e.g.,":[56],"Jaccard":[59],"edit":[62],"distance.":[63],"However,":[64],"this":[65,106],"significantly":[66,119],"increases":[67],"verification":[69],"cost,":[70],"making":[71],"even":[72,126],"more":[73,120],"need":[76,142],"for":[77,143],"efficient":[78],"effective":[80],"filtering":[81],"techniques":[82],"reduce":[84,154],"number":[86],"candidate":[88],"pairs.":[89],"The":[90],"current":[91],"state-of-the-art":[92],"algorithm":[93],"relies":[94],"computations":[97],"between":[98],"elements":[101],"filter":[103],"candidates.":[104],"In":[105],"paper,":[107],"we":[108,131],"propose":[109,150],"token-based":[110],"element-based":[113],"filtering,":[114],"showing":[115],"that":[116,167],"it":[117],"lightweight,":[121],"while":[122],"offering":[123],"similar":[124],"better":[127],"pruning":[128],"effectiveness.":[129],"Moreover,":[130],"address":[132],"top-":[134],"k":[135],"variant":[136],"problem,":[139],"alleviating":[140],"a":[144],"user-specified":[145],"threshold.":[147],"We":[148],"early":[151],"termination":[152],"cost":[156],"verification.":[158],"Our":[159],"experimental":[160],"results":[161],"six":[163],"real-world":[164],"datasets":[165],"show":[166],"our":[168],"approach":[169],"always":[170],"outperforms":[171],"state":[173],"art,":[176],"being":[177],"order":[179],"magnitude":[181],"faster":[182],"average.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2023-02-10T00:00:00"}