{"id":"https://openalex.org/W3136558723","doi":"https://doi.org/10.14778/2809974.2809976","title":"Scaling similarity joins over tree-structured data","display_name":"Scaling similarity joins over tree-structured data","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W3136558723","doi":"https://doi.org/10.14778/2809974.2809976","mag":"3136558723"},"language":"en","primary_location":{"id":"doi:10.14778/2809974.2809976","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2809974.2809976","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":"http://infoscience.epfl.ch/record/213919","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045136220","display_name":"Yu Tang","orcid":"https://orcid.org/0000-0001-5231-6347"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CH","HK"],"is_corresponding":true,"raw_author_name":"Yu Tang","raw_affiliation_strings":["The University of Hong Kong and EPFL Switzerland"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong and EPFL Switzerland","institution_ids":["https://openalex.org/I5124864","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091236531","display_name":"Yilun Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yilun Cai","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045731304","display_name":"Nikos Mamoulis","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nikos Mamoulis","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045136220"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.8616,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.76888993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":"11","first_page":"1130","last_page":"1141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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":0.9977999925613403,"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"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8391311168670654},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.695703387260437},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6910098791122437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5840823650360107},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5457796454429626},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.49346816539764404},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4734601378440857},{"id":"https://openalex.org/keywords/similitude","display_name":"Similitude","score":0.41005176305770874},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40760326385498047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3703192472457886},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35907110571861267},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3262515366077423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2651267349720001},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.22689488530158997},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07638409733772278}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8391311168670654},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.695703387260437},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6910098791122437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5840823650360107},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5457796454429626},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.49346816539764404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4734601378440857},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.41005176305770874},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40760326385498047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3703192472457886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35907110571861267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3262515366077423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2651267349720001},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.22689488530158997},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07638409733772278},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/2809974.2809976","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2809974.2809976","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:hub.hku.hk:10722/213720","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/213720","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"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_Paper"},{"id":"pmh:oai:infoscience.tind.io:213919","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/213919","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"","raw_type":"research article"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:213919","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/213919","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"","raw_type":"research article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W984076445","https://openalex.org/W1571338321","https://openalex.org/W1875120328","https://openalex.org/W1966139659","https://openalex.org/W1969712592","https://openalex.org/W1973001156","https://openalex.org/W1975009259","https://openalex.org/W1976373002","https://openalex.org/W1986037284","https://openalex.org/W2003889154","https://openalex.org/W2005450316","https://openalex.org/W2010916971","https://openalex.org/W2022979132","https://openalex.org/W2052581258","https://openalex.org/W2065110301","https://openalex.org/W2068665379","https://openalex.org/W2079698247","https://openalex.org/W2085922539","https://openalex.org/W2107412086","https://openalex.org/W2122092469","https://openalex.org/W2133378824","https://openalex.org/W2138007734","https://openalex.org/W2147828873","https://openalex.org/W2162675341","https://openalex.org/W2171643895","https://openalex.org/W2251939518","https://openalex.org/W3104921985","https://openalex.org/W6635494053","https://openalex.org/W6786301650"],"related_works":["https://openalex.org/W2608731915","https://openalex.org/W2128582123","https://openalex.org/W2963940951","https://openalex.org/W2363930051","https://openalex.org/W575918167","https://openalex.org/W2594505223","https://openalex.org/W2371125232","https://openalex.org/W2796483994","https://openalex.org/W2105436061","https://openalex.org/W2037562342"],"abstract_inverted_index":{"Given":[0],"a":[1,26,30,75,133],"large":[2],"collection":[3],"of":[4,16,43,57,87,158],"tree-structured":[5],"objects":[6,17,45,90,111],"(e.g.,":[7,46],"XML":[8],"documents),":[9],"the":[10,14,44,58,68,84,88,95,102,110,125,127,150],"similarity":[11,27,37,59,77,96],"join":[12,38,60,78],"finds":[13],"pairs":[15,52],"that":[18,53,146],"are":[19,130],"similar":[20],"to":[21,50,94,122,155],"each":[22],"other,":[23],"based":[24,62,82],"on":[25,63,83,139],"threshold":[28],"and":[29,141],"tree":[31,89,107],"edit":[32],"distance":[33,64,104],"measure.":[34],"The":[35],"state-of-the-art":[36,151],"methods":[39,152],"compare":[40],"simpler":[41],"approximations":[42],"strings),":[47],"in":[48,132],"order":[49,121,157],"prune":[51],"cannot":[54],"be":[55],"part":[56],"result":[61],"bounds":[65],"derived":[66],"by":[67,153],"approximations.":[69],"In":[70,120],"this":[71],"paper,":[72],"we":[73],"propose":[74],"novel":[76],"approach,":[79],"which":[80],"is":[81],"dynamic":[85],"decomposition":[86],"into":[91],"subgraphs,":[92],"according":[93],"threshold.":[97],"Our":[98,136],"technique":[99],"avoids":[100],"computing":[101],"exact":[103],"between":[105],"two":[106],"objects,":[108],"if":[109],"do":[112],"not":[113],"share":[114],"at":[115],"least":[116],"one":[117],"common":[118],"subgraph.":[119],"scale":[123],"up":[124,154],"join,":[126],"computed":[128],"subgraphs":[129],"managed":[131],"two-layer":[134],"index.":[135],"experimental":[137],"results":[138],"real":[140],"synthetic":[142],"data":[143],"collections":[144],"show":[145],"our":[147],"approach":[148],"outperforms":[149],"an":[156],"magnitude.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}