{"id":"https://openalex.org/W2513214219","doi":"https://doi.org/10.1109/tkde.2016.2601325","title":"K-Join: Knowledge-Aware Similarity Join","display_name":"K-Join: Knowledge-Aware Similarity Join","publication_year":2016,"publication_date":"2016-09-05","ids":{"openalex":"https://openalex.org/W2513214219","doi":"https://doi.org/10.1109/tkde.2016.2601325","mag":"2513214219"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2016.2601325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2601325","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5007330751","display_name":"Zeyuan Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zeyuan Shang","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China","Department of Computer Science, Tsinghua University, Beijing, CHINA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, CHINA","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079584546","display_name":"Yaxiao Liu","orcid":"https://orcid.org/0000-0001-6053-0757"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxiao Liu","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China","Department of Computer Science, Tsinghua University, Beijing, CHINA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, CHINA","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451576","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0002-1398-0621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Li","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China","Department of Computer Science, Tsinghua University, Beijing, CHINA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, CHINA","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100951661","display_name":"Jianhua Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Feng","raw_affiliation_strings":["Department of Computer Science, Tsinghua University, Beijing, China","Department of Computer Science, Tsinghua University, Beijing, CHINA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science, Tsinghua University, Beijing, CHINA","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007330751"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":6.1039,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.96274437,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"28","issue":"12","first_page":"3293","last_page":"3308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9922000169754028,"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/computer-science","display_name":"Computer science","score":0.8034372329711914},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7131862640380859},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6872137784957886},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6104155778884888},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5245193243026733},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49194929003715515},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47313204407691956},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4536943733692169},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4298423230648041},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4263780415058136},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36988306045532227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23169419169425964},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09789919853210449},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09536555409431458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034372329711914},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7131862640380859},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6872137784957886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6104155778884888},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5245193243026733},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49194929003715515},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47313204407691956},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4536943733692169},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4298423230648041},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4263780415058136},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36988306045532227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23169419169425964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09789919853210449},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09536555409431458},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2016.2601325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2016.2601325","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2024795505","display_name":null,"funder_award_id":"61472198","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5452479108","display_name":null,"funder_award_id":"61373024","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5652550493","display_name":null,"funder_award_id":"61632016","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7656227776","display_name":null,"funder_award_id":"2012AA012600","funder_id":"https://openalex.org/F4320335773","funder_display_name":"National High-tech Research and Development Program"},{"id":"https://openalex.org/G978999948","display_name":null,"funder_award_id":"61422205","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1496255159","https://openalex.org/W1536525420","https://openalex.org/W1567171318","https://openalex.org/W1591155856","https://openalex.org/W1645638879","https://openalex.org/W1973001156","https://openalex.org/W1990947147","https://openalex.org/W1991175610","https://openalex.org/W1999916788","https://openalex.org/W2001700730","https://openalex.org/W2009899413","https://openalex.org/W2039789840","https://openalex.org/W2044163187","https://openalex.org/W2056748234","https://openalex.org/W2065758089","https://openalex.org/W2072173758","https://openalex.org/W2073329022","https://openalex.org/W2073540046","https://openalex.org/W2096076988","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2100548092","https://openalex.org/W2106675345","https://openalex.org/W2108991785","https://openalex.org/W2115214414","https://openalex.org/W2115215982","https://openalex.org/W2117974736","https://openalex.org/W2119057313","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2125980212","https://openalex.org/W2127675794","https://openalex.org/W2136480620","https://openalex.org/W2148148676","https://openalex.org/W2150916025","https://openalex.org/W2157233202","https://openalex.org/W2158779275","https://openalex.org/W2163051926","https://openalex.org/W2166400748","https://openalex.org/W2167331726","https://openalex.org/W2167847032","https://openalex.org/W2217456271","https://openalex.org/W2286724461","https://openalex.org/W2294331997","https://openalex.org/W3146259567","https://openalex.org/W6633813756","https://openalex.org/W6635148446","https://openalex.org/W6677631532"],"related_works":["https://openalex.org/W3214148052","https://openalex.org/W2151692181","https://openalex.org/W794462722","https://openalex.org/W2029625042","https://openalex.org/W4248476017","https://openalex.org/W2807741550","https://openalex.org/W2970426051","https://openalex.org/W1525319740","https://openalex.org/W4247864646","https://openalex.org/W1484210779"],"abstract_inverted_index":{"Similarity":[0],"join":[1],"is":[2,93,108,117],"a":[3,70,132,148],"fundamental":[4],"operation":[5],"in":[6,34,183,200],"data":[7],"cleaning":[8],"and":[9,45,73,170,205],"integration.":[10],"Existing":[11],"similarity-join":[12],"methods":[13],"utilize":[14],"the":[15,20,24,27,36,53,87,94,112,122,138,142,154,177,184],"string":[16],"similarity":[17,57,66,99,134,140],"to":[18,39,51,55,110,119,136,151,163,175],"quantify":[19,111,137],"relevance":[21],"but":[22],"neglect":[23],"knowledge":[25,41,54,71,143],"behind":[26],"data,":[28],"which":[29],"plays":[30],"an":[31,49],"important":[32],"role":[33],"understanding":[35],"data.":[37],"Thanks":[38],"public":[40],"bases,":[42],"e.g.,":[43],"Freebase":[44],"Yago,":[46],"we":[47,63,129],"have":[48],"opportunity":[50],"use":[52],"improve":[56],"join.":[58,100],"To":[59,86,125],"address":[60,126],"this":[61,92],"problem,":[62],"study":[64,96],"knowledge-aware":[65,82,98,113,139],"join,":[67],"which,":[68],"given":[69],"hierarchy":[72],"two":[74,103],"collections":[75],"of":[76,89,167,202],"objects":[77],"(e.g.,":[78],"documents),":[79],"finds":[80],"all":[81],"similar":[83,123,155],"object":[84],"pairs.":[85,124,156],"best":[88],"our":[90,194],"knowledge,":[91],"first":[95,107,130],"on":[97,189],"There":[101],"are":[102,180],"main":[104],"challenges.":[105],"The":[106,115],"how":[109,118],"similarity.":[114],"second":[116],"efficiently":[120,152],"identify":[121,153],"these":[127],"challenges,":[128],"propose":[131,158],"new":[133],"metric":[135],"using":[141],"hierarchy.":[144],"We":[145,157],"then":[146],"devise":[147],"filter-and-verification":[149],"framework":[150],"effective":[159],"signature-based":[160],"filtering":[161],"techniques":[162],"prune":[164],"large":[165],"numbers":[166],"dissimilar":[168],"pairs":[169],"develop":[171],"efficient":[172],"verification":[173],"algorithms":[174,199],"verify":[176],"candidates":[178],"that":[179,193],"not":[181],"pruned":[182],"filter":[185],"step.":[186],"Experimental":[187],"results":[188],"real-world":[190],"datasets":[191],"show":[192],"method":[195],"significantly":[196],"outperforms":[197],"baseline":[198],"terms":[201],"both":[203],"efficiency":[204],"effectiveness.":[206]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}