{"id":"https://openalex.org/W2024988577","doi":"https://doi.org/10.1109/tkde.2014.2373385","title":"Top-k Similarity Join in Heterogeneous Information Networks","display_name":"Top-k Similarity Join in Heterogeneous Information Networks","publication_year":2014,"publication_date":"2014-11-20","ids":{"openalex":"https://openalex.org/W2024988577","doi":"https://doi.org/10.1109/tkde.2014.2373385","mag":"2024988577"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2014.2373385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2014.2373385","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/A5001877137","display_name":"Yun Xiong","orcid":"https://orcid.org/0000-0002-8575-5415"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yun Xiong","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, P.R. China","Shanghai Key Laboratory of Data Science Fudan University Shanghai P. R. China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science Fudan University Shanghai P. R. China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020370754","display_name":"Yangyong Zhu","orcid":"https://orcid.org/0000-0002-6258-0747"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyong Zhu","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, P.R. China","Shanghai Key Laboratory of Data Science Fudan University Shanghai P. R. China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, P.R. China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science Fudan University Shanghai P. R. China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Chicago, 851 S. Morgan St., IL, Chicago"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Chicago, 851 S. Morgan St., IL, Chicago","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001877137"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":3.9019,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.94959219,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"27","issue":"6","first_page":"1710","last_page":"1723"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9973000288009644,"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/T11478","display_name":"Caching and Content Delivery","score":0.9944000244140625,"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":0.7662659883499146},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.736292839050293},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6163932085037231},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5718564987182617},{"id":"https://openalex.org/keywords/hash-join","display_name":"Hash join","score":0.533364474773407},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5227277874946594},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5008645057678223},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4618951082229614},{"id":"https://openalex.org/keywords/sort-merge-join","display_name":"Sort-merge join","score":0.45927032828330994},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4452784061431885},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4404159188270569},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.43799182772636414},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4319969415664673},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43039727210998535},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43000710010528564},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.42288652062416077},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3912678360939026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2247903048992157},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1690773367881775},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.1394326388835907},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11842089891433716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7662659883499146},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.736292839050293},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6163932085037231},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5718564987182617},{"id":"https://openalex.org/C188805328","wikidata":"https://www.wikidata.org/wiki/Q4060691","display_name":"Hash join","level":3,"score":0.533364474773407},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5227277874946594},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5008645057678223},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4618951082229614},{"id":"https://openalex.org/C203570394","wikidata":"https://www.wikidata.org/wiki/Q4060688","display_name":"Sort-merge join","level":3,"score":0.45927032828330994},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4452784061431885},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4404159188270569},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.43799182772636414},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4319969415664673},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43039727210998535},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43000710010528564},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.42288652062416077},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3912678360939026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2247903048992157},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1690773367881775},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.1394326388835907},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11842089891433716},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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:10.1109/tkde.2014.2373385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2014.2373385","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":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G260777838","display_name":null,"funder_award_id":"OISE-1129076","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3409880724","display_name":null,"funder_award_id":"NSFC-61170096","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"},{"id":"https://openalex.org/G5797485025","display_name":null,"funder_award_id":"13dz2260200","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"},{"id":"https://openalex.org/G6302867500","display_name":null,"funder_award_id":"CNS-1115234","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6730199920","display_name":null,"funder_award_id":"13511504300","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321655","display_name":"Science and Technology Development Fund","ror":"https://ror.org/044vr6g03"},{"id":"https://openalex.org/F4320328656","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W102116019","https://openalex.org/W103340358","https://openalex.org/W141197097","https://openalex.org/W1502916507","https://openalex.org/W1539585011","https://openalex.org/W1979075286","https://openalex.org/W1985123706","https://openalex.org/W2000482994","https://openalex.org/W2012833704","https://openalex.org/W2033175785","https://openalex.org/W2057169561","https://openalex.org/W2063149926","https://openalex.org/W2063999654","https://openalex.org/W2069153192","https://openalex.org/W2069870183","https://openalex.org/W2098711168","https://openalex.org/W2102848467","https://openalex.org/W2104324457","https://openalex.org/W2105436061","https://openalex.org/W2106184958","https://openalex.org/W2107427524","https://openalex.org/W2110896767","https://openalex.org/W2111607365","https://openalex.org/W2117831564","https://openalex.org/W2117974736","https://openalex.org/W2121269638","https://openalex.org/W2123561513","https://openalex.org/W2141115343","https://openalex.org/W2145349611","https://openalex.org/W2147717514","https://openalex.org/W2148781362","https://openalex.org/W2150916025","https://openalex.org/W2156855109","https://openalex.org/W2167331726","https://openalex.org/W2169189402","https://openalex.org/W2170037597","https://openalex.org/W2397770138","https://openalex.org/W4230940751","https://openalex.org/W6629956336","https://openalex.org/W6644822220","https://openalex.org/W6666455921","https://openalex.org/W6675292945","https://openalex.org/W6675610486","https://openalex.org/W6675988575","https://openalex.org/W6681490311","https://openalex.org/W6685012337"],"related_works":["https://openalex.org/W2381211091","https://openalex.org/W2091359263","https://openalex.org/W4283362132","https://openalex.org/W4234452035","https://openalex.org/W2469706965","https://openalex.org/W4205996836","https://openalex.org/W1866159721","https://openalex.org/W1589496614","https://openalex.org/W1989231289","https://openalex.org/W3033055359"],"abstract_inverted_index":{"As":[0],"a":[1,32,111,134],"newly":[2],"emerging":[3],"network":[4,47],"model,":[5],"heterogeneous":[6,75,135],"information":[7,136],"networks":[8],"(HINs)":[9],"have":[10,18],"received":[11],"growing":[12],"attention.":[13],"Many":[14],"data":[15,174],"mining":[16],"tasks":[17],"been":[19,62,72],"explored":[20],"in":[21,65,74,133],"HINs,":[22],"including":[23],"clustering,":[24],"classification,":[25],"and":[26,55,94,101,179],"similarity":[27,59,84,113,144,168],"search.":[28],"Similarity":[29,160],"join":[30,60,85,114,131,161],"is":[31,40],"fundamental":[33],"operation":[34],"required":[35],"for":[36],"many":[37],"problems.":[38],"It":[39],"attracting":[41],"attention":[42],"from":[43],"various":[44,167],"applications":[45],"on":[46,83,127,172],"data,":[48],"such":[49],"as":[50],"friend":[51],"recommendation,":[52],"link":[53],"prediction,":[54],"online":[56],"advertising.":[57],"Although":[58],"has":[61,69],"well":[63],"studied":[64,73],"homogeneous":[66],"networks,":[67],"it":[68],"not":[70],"yet":[71],"networks.":[76],"Especially,":[77],"none":[78],"of":[79,103,124,181],"the":[80,99,104,119,177,182],"existing":[81,158],"research":[82],"takes":[86],"different":[87],"semantic":[88],"meanings":[89],"behind":[90],"paths":[91],"into":[92],"consideration":[93],"almost":[95],"all":[96],"completely":[97],"ignore":[98],"heterogeneity":[100],"diversity":[102],"HINs.":[105],"In":[106],"this":[107],"paper,":[108],"we":[109],"propose":[110],"path-based":[112],"(PS-join)":[115],"method":[116],"to":[117,141],"return":[118],"top":[120],"k":[121],"similar":[122],"pairs":[123],"objects":[125],"based":[126,150],"any":[128],"user":[129],"specified":[130],"path":[132],"network.":[137],"We":[138],"study":[139],"how":[140],"prune":[142],"expensive":[143],"computation":[145],"by":[146],"introducing":[147],"bucket":[148],"pruning":[149],"locality":[151],"sensitive":[152],"hashing":[153],"(BPLSH)":[154],"indexing.":[155],"Compared":[156],"with":[157],"Link-based":[159],"(LS-join)":[162],"method,":[163],"PS-join":[164],"can":[165],"derive":[166],"semantics.":[169],"Experimental":[170],"results":[171],"real":[173],"sets":[175],"show":[176],"efficiency":[178],"effectiveness":[180],"proposed":[183],"approach.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-02-19T06:27:42.648592","created_date":"2025-10-10T00:00:00"}