{"id":"https://openalex.org/W2107412086","doi":"https://doi.org/10.1145/1066157.1066243","title":"Similarity evaluation on tree-structured data","display_name":"Similarity evaluation on tree-structured data","publication_year":2005,"publication_date":"2005-06-14","ids":{"openalex":"https://openalex.org/W2107412086","doi":"https://doi.org/10.1145/1066157.1066243","mag":"2107412086"},"language":"en","primary_location":{"id":"doi:10.1145/1066157.1066243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030499511","display_name":"Rui Yang","orcid":"https://orcid.org/0000-0002-5634-5476"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rui Yang","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014399734","display_name":"Panos Kalnis","orcid":"https://orcid.org/0000-0002-5060-1360"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Panos Kalnis","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023925931","display_name":"Anthony K. H. Tung","orcid":"https://orcid.org/0000-0002-5125-855X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Anthony K. H. Tung","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":12.226,"has_fulltext":false,"cited_by_count":166,"citation_normalized_percentile":{"value":0.99215131,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"754","last_page":"765"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9980000257492065,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965999722480774,"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/edit-distance","display_name":"Edit distance","score":0.8535149097442627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6746121644973755},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6491560935974121},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6173995137214661},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5360659956932068},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.48626863956451416},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46961766481399536},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4667169451713562},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.42325595021247864},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.41986536979675293},{"id":"https://openalex.org/keywords/distance-measures","display_name":"Distance measures","score":0.41175705194473267},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3637810945510864},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36166149377822876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28184980154037476},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2707805037498474},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.2495606541633606},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06566917896270752}],"concepts":[{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.8535149097442627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746121644973755},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6491560935974121},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6173995137214661},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5360659956932068},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.48626863956451416},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46961766481399536},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4667169451713562},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.42325595021247864},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.41986536979675293},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.41175705194473267},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3637810945510864},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36166149377822876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28184980154037476},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2707805037498474},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.2495606541633606},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06566917896270752},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1066157.1066243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/41283","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/41283","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","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":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W7950900","https://openalex.org/W1541459201","https://openalex.org/W1875120328","https://openalex.org/W1887000090","https://openalex.org/W1976373002","https://openalex.org/W2025364575","https://openalex.org/W2030766291","https://openalex.org/W2038044292","https://openalex.org/W2043481183","https://openalex.org/W2046953300","https://openalex.org/W2048001624","https://openalex.org/W2092057784","https://openalex.org/W2097704312","https://openalex.org/W2105022522","https://openalex.org/W2115579441","https://openalex.org/W2118269922","https://openalex.org/W2134627110","https://openalex.org/W2141196435","https://openalex.org/W2147828873","https://openalex.org/W2161936973","https://openalex.org/W2164501930","https://openalex.org/W2586374872","https://openalex.org/W2752853835","https://openalex.org/W4238690227"],"related_works":["https://openalex.org/W1516985461","https://openalex.org/W1974646519","https://openalex.org/W124283286","https://openalex.org/W1550039237","https://openalex.org/W2180288160","https://openalex.org/W3106798595","https://openalex.org/W1579746959","https://openalex.org/W2069148796","https://openalex.org/W2102177745","https://openalex.org/W2052451333"],"abstract_inverted_index":{"Tree-structured":[0],"data":[1,63],"are":[2],"becoming":[3],"ubiquitous":[4],"nowadays":[5],"and":[6],"manipulating":[7],"them":[8],"based":[9],"on":[10,104,126,152],"similarity":[11,20,29,124,149],"is":[12,24,39,89,144],"essential":[13],"for":[14,22,36,97,147],"many":[15],"applications.":[16],"The":[17,129],"generally":[18],"accepted":[19],"measure":[21],"trees":[23,38,154],"the":[25,46,51,72,79,83,98,105,115,138],"edit":[26,53,99],"distance.":[27,54],"Although":[28],"search":[30,125],"has":[31],"been":[32],"extensively":[33],"studied,":[34],"searching":[35],"similar":[37],"still":[40],"an":[41,65],"open":[42],"problem":[43],"due":[44],"to":[45,60,122],"high":[47],"complexity":[48,88],"of":[49,82],"computing":[50],"tree":[52],"In":[55],"this":[56],"paper,":[57],"we":[58,108],"propose":[59],"transform":[61],"tree-structured":[62,127],"into":[64,118],"approximate":[66],"numerical":[67],"multidimensional":[68],"vector":[69],"which":[70,113],"encodes":[71],"original":[73],"structure":[74],"information.":[75],"We":[76],"prove":[77],"that":[78,133],"L1":[80],"distance":[81,100,117,139],"corresponding":[84],"vectors,":[85],"whose":[86],"computational":[87],"O(|T1|":[90],"+":[91],"|T2|),":[92],"forms":[93],"a":[94,110,119],"lower":[95],"bound":[96],"between":[101],"trees.":[102],"Based":[103],"theoretical":[106],"analysis,":[107],"describe":[109],"novel":[111],"algorithm":[112,135],"embeds":[114],"proposed":[116],"filter-and-refine":[120],"framework":[121],"process":[123],"data.":[128],"experimental":[130],"results":[131],"show":[132],"our":[134],"reduces":[136],"dramatically":[137],"computation":[140],"cost.":[141],"Our":[142],"method":[143],"especially":[145],"suitable":[146],"accelerating":[148],"query":[150],"processing":[151],"large":[153],"in":[155],"massive":[156],"datasets.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}