{"id":"https://openalex.org/W2068395804","doi":"https://doi.org/10.1145/1376815.1376818","title":"Tree model guided candidate generation for mining frequent subtrees from XML documents","display_name":"Tree model guided candidate generation for mining frequent subtrees from XML documents","publication_year":2008,"publication_date":"2008-07-01","ids":{"openalex":"https://openalex.org/W2068395804","doi":"https://doi.org/10.1145/1376815.1376818","mag":"2068395804"},"language":"en","primary_location":{"id":"doi:10.1145/1376815.1376818","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376815.1376818","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"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":"ACM Transactions on Knowledge Discovery from Data","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/A5111780030","display_name":"Henry Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Henry Tan","raw_affiliation_strings":["Univ. of Technology Sydney, Australia","Univ. of Technology/Sydney (Australia)"],"affiliations":[{"raw_affiliation_string":"Univ. of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"Univ. of Technology/Sydney (Australia)","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010008969","display_name":"Fedja Hadzic","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fedja Hadzic","raw_affiliation_strings":["Univ. of Technology Sydney, Australia","Univ. of Technology/Sydney (Australia)"],"affiliations":[{"raw_affiliation_string":"Univ. of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"Univ. of Technology/Sydney (Australia)","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049421085","display_name":"Tharam S. Dillon","orcid":"https://orcid.org/0000-0002-7527-129X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tharam S. Dillon","raw_affiliation_strings":["Univ. of Technology Sydney, Australia","Univ. of Technology/Sydney (Australia)"],"affiliations":[{"raw_affiliation_string":"Univ. of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"Univ. of Technology/Sydney (Australia)","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031465905","display_name":"Elizabeth Chang","orcid":"https://orcid.org/0000-0002-4439-1854"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Elizabeth Chang","raw_affiliation_strings":["Curtin Univ. of Technology, Perth, Australia"],"affiliations":[{"raw_affiliation_string":"Curtin Univ. of Technology, Perth, Australia","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101756436","display_name":"Ling Feng","orcid":"https://orcid.org/0000-0001-7378-4342"},"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":"Ling Feng","raw_affiliation_strings":["Tsinghua Univ., China","#N##TAB##TAB##TAB##TAB# Tsinghua University, China#N##TAB##TAB##TAB#"],"affiliations":[{"raw_affiliation_string":"Tsinghua Univ., China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Tsinghua University, China#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111780030"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":19.4571,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.99096771,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2","issue":"2","first_page":"1","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9890000224113464,"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/T11106","display_name":"Data Management and Algorithms","score":0.9883000254631042,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8193478584289551},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6683777570724487},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6355973482131958},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.5731901526451111},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5230932235717773},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5214128494262695},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.47922569513320923},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.44524919986724854},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44299179315567017},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38324832916259766},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3204463720321655},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3190211057662964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.195307195186615},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18941181898117065},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.15872636437416077},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1414586305618286},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10255753993988037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8193478584289551},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6683777570724487},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6355973482131958},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.5731901526451111},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5230932235717773},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5214128494262695},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.47922569513320923},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.44524919986724854},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44299179315567017},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38324832916259766},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3204463720321655},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3190211057662964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.195307195186615},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18941181898117065},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.15872636437416077},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1414586305618286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10255753993988037},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1376815.1376818","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376815.1376818","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"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":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W56896489","https://openalex.org/W1482003340","https://openalex.org/W1488173605","https://openalex.org/W1506285740","https://openalex.org/W1514542003","https://openalex.org/W1536535841","https://openalex.org/W1536540269","https://openalex.org/W1553696291","https://openalex.org/W1593813215","https://openalex.org/W1981755487","https://openalex.org/W1990483472","https://openalex.org/W2009758120","https://openalex.org/W2012537185","https://openalex.org/W2023695596","https://openalex.org/W2037965136","https://openalex.org/W2064853889","https://openalex.org/W2074700442","https://openalex.org/W2080632942","https://openalex.org/W2099962227","https://openalex.org/W2100588761","https://openalex.org/W2103033326","https://openalex.org/W2121313660","https://openalex.org/W2121422364","https://openalex.org/W2122303450","https://openalex.org/W2133378824","https://openalex.org/W2135552269","https://openalex.org/W2140158493","https://openalex.org/W2140900696","https://openalex.org/W2141115288","https://openalex.org/W2144481322","https://openalex.org/W2144903778","https://openalex.org/W2158454296","https://openalex.org/W2164611973","https://openalex.org/W2166559705","https://openalex.org/W2168209541","https://openalex.org/W2170726034","https://openalex.org/W2171187485","https://openalex.org/W2252984047","https://openalex.org/W2280339874","https://openalex.org/W2569183226","https://openalex.org/W3039539181","https://openalex.org/W6602051145","https://openalex.org/W6629155293","https://openalex.org/W6674917368","https://openalex.org/W6685146747"],"related_works":["https://openalex.org/W3110783709","https://openalex.org/W2372453241","https://openalex.org/W2371387875","https://openalex.org/W2531660186","https://openalex.org/W2064670891","https://openalex.org/W2025988984","https://openalex.org/W1508699539","https://openalex.org/W2030846031","https://openalex.org/W2349743712","https://openalex.org/W2227630426"],"abstract_inverted_index":{"Due":[0],"to":[1,127,148],"the":[2,95,122,128,132,149,176,202,205,208],"inherent":[3],"flexibilities":[4],"in":[5],"both":[6,186],"structure":[7,24],"and":[8,25,77,140,162,188,198,204],"semantics,":[9],"XML":[10,33,47,57],"association":[11],"rules":[12],"mining":[13,39,74,196],"faces":[14],"few":[15],"challenges,":[16],"such":[17],"as:":[18],"a":[19,44,54,60,137],"more":[20],"complicated":[21],"hierarchical":[22],"data":[23,27],"ordered":[26,65,79],"context.":[28],"Mining":[29],"frequent":[30,40,75],"patterns":[31],"from":[32,43],"documents":[34,58],"can":[35],"be":[36],"recast":[37],"as":[38,59,85],"tree":[41,96],"structures":[42],"database":[45,55,61],"of":[46,56,62,94,102,131,179,207],"documents.":[48],"In":[49,67,154],"this":[50,155],"study,":[51],"we":[52,69,157],"model":[53,139],"rooted":[63],"labeled":[64],"subtrees.":[66,80,167],"particular,":[68],"are":[70,84],"mainly":[71],"concerned":[72],"with":[73,185],"induced":[76,170,197],"embedded":[78,166,172,199],"Our":[81,183],"main":[82],"contributions":[83],"follows.":[86],"We":[87,134],"describe":[88],"our":[89,103],"unique":[90],"embedding":[91,180],"list":[92],"representation":[93],"structure,":[97],"which":[98],"enables":[99],"efficient":[100],"implementation":[101],"Tree":[104],"Model":[105],"Guided":[106],"(":[107],"TMG":[108,112,143],")":[109],"candidate":[110],"generation.":[111],"is":[113],"an":[114],"optimal,":[115],"nonredundant":[116],"enumeration":[117],"strategy":[118],"that":[119,125,142],"enumerates":[120],"all":[121],"valid":[123],"candidates":[124],"conform":[126],"structural":[129],"aspects":[130],"data.":[133],"show":[135],"through":[136],"mathematical":[138],"experiments":[141,184],"has":[144],"better":[145],"complexity":[146],"compared":[147],"commonly":[150],"used":[151],"join":[152],"approach.":[153],"article,":[156],"propose":[158],"two":[159,192],"algorithms,":[160],"MB3-Miner":[161,164],"iMB3-Miner.":[163],"mines":[165,169],"iMB3-Miner":[168],"and/or":[171],"subtrees":[173],"by":[174],"using":[175],"maximum":[177],"level":[178],"constraint":[181],".":[182],"synthetic":[187],"real":[189],"datasets":[190],"against":[191],"well-known":[193],"algorithms":[194],"for":[195],"subtrees,":[200],"demonstrate":[201],"effectiveness":[203],"efficiency":[206],"proposed":[209],"techniques.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}