{"id":"https://openalex.org/W2624006284","doi":"https://doi.org/10.1145/3085504.3085518","title":"Active Learning with Density-Initialized Decision Tree for Record Matching","display_name":"Active Learning with Density-Initialized Decision Tree for Record Matching","publication_year":2017,"publication_date":"2017-06-05","ids":{"openalex":"https://openalex.org/W2624006284","doi":"https://doi.org/10.1145/3085504.3085518","mag":"2624006284"},"language":"en","primary_location":{"id":"doi:10.1145/3085504.3085518","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3085504.3085518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-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/A5090458924","display_name":"Chenxiao Dou","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Chenxiao Dou","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008497202","display_name":"Daniel Sun","orcid":"https://orcid.org/0000-0003-2342-7421"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Daniel Sun","raw_affiliation_strings":["CSIRO, University of New South Wales, Shanghai Jiao Tong University, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"CSIRO, University of New South Wales, Shanghai Jiao Tong University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571","https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354142","display_name":"Guoqiang Li","orcid":"https://orcid.org/0000-0001-9005-7112"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqiang Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015158455","display_name":"Raymond K. Wong","orcid":"https://orcid.org/0000-0002-9814-6029"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Raymond K. Wong","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090458924"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.5167,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70413945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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/T10028","display_name":"Topic Modeling","score":0.9894999861717224,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9861999750137329,"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":0.7655177116394043},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7251465320587158},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7187556028366089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6451742649078369},{"id":"https://openalex.org/keywords/labelling","display_name":"Labelling","score":0.6311914324760437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.577446460723877},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5359751582145691},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.500079870223999},{"id":"https://openalex.org/keywords/incremental-decision-tree","display_name":"Incremental decision tree","score":0.44266119599342346},{"id":"https://openalex.org/keywords/decision-tree-learning","display_name":"Decision tree learning","score":0.3824441432952881},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37563201785087585},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3245798647403717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655177116394043},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7251465320587158},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7187556028366089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6451742649078369},{"id":"https://openalex.org/C2780523633","wikidata":"https://www.wikidata.org/wiki/Q380709","display_name":"Labelling","level":2,"score":0.6311914324760437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.577446460723877},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5359751582145691},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.500079870223999},{"id":"https://openalex.org/C10229987","wikidata":"https://www.wikidata.org/wiki/Q17083028","display_name":"Incremental decision tree","level":4,"score":0.44266119599342346},{"id":"https://openalex.org/C5481197","wikidata":"https://www.wikidata.org/wiki/Q16766476","display_name":"Decision tree learning","level":3,"score":0.3824441432952881},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37563201785087585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3245798647403717},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3085504.3085518","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3085504.3085518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W154872207","https://openalex.org/W1550206324","https://openalex.org/W1564285798","https://openalex.org/W1646278814","https://openalex.org/W2031250218","https://openalex.org/W2052698082","https://openalex.org/W2067566391","https://openalex.org/W2079649893","https://openalex.org/W2080021732","https://openalex.org/W2095644746","https://openalex.org/W2098203240","https://openalex.org/W2106675345","https://openalex.org/W2107966677","https://openalex.org/W2108991785","https://openalex.org/W2111116800","https://openalex.org/W2111625757","https://openalex.org/W2117974736","https://openalex.org/W2119320829","https://openalex.org/W2125055259","https://openalex.org/W2129598390","https://openalex.org/W2132791018","https://openalex.org/W2139077857","https://openalex.org/W2143124645","https://openalex.org/W2148143831","https://openalex.org/W2161336914","https://openalex.org/W2164456230","https://openalex.org/W2169585110","https://openalex.org/W2170039925","https://openalex.org/W2288790589","https://openalex.org/W2426031434","https://openalex.org/W2563121713","https://openalex.org/W2585642343","https://openalex.org/W2596610888","https://openalex.org/W2903158431","https://openalex.org/W4214588406","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2030894524","https://openalex.org/W1982169401","https://openalex.org/W1648970942","https://openalex.org/W2811372817","https://openalex.org/W2120748120","https://openalex.org/W2545418239","https://openalex.org/W2591672004","https://openalex.org/W4243803609","https://openalex.org/W4319437832","https://openalex.org/W2350430350"],"abstract_inverted_index":{"One":[0,43],"of":[1,44,48,115,155],"the":[2,23,45,93,110],"fundamental":[3],"problem":[4],"in":[5,73],"data":[6,9,28],"management":[7],"and":[8],"integration":[10],"fields":[11],"is":[12,51,81,91],"Record":[13],"Matching,":[14],"which":[15,59],"refers":[16],"to":[17,22,37,52,108],"identifying":[18],"records":[19],"that":[20,140],"relate":[21],"same":[24],"entities":[25],"across":[26],"different":[27],"sources.":[29],"In":[30,100],"recent":[31],"literature,":[32],"active":[33,49,60,130,156],"learning":[34,50,61,145],"has":[35],"demonstrated":[36],"be":[38,97],"effective":[39],"for":[40,68,78,133],"record":[41],"matching.":[42],"key":[46],"steps":[47],"build":[53],"a":[54,87],"proper":[55],"initial":[56,89,111],"classifier,":[57],"with":[58,147],"algorithms":[62],"can":[63,96],"quickly":[64],"locate":[65],"informative":[66,135],"examples":[67],"training":[69,80],"accurate":[70],"models.":[71],"However,":[72],"this":[74,101],"process,":[75],"example":[76],"labelling":[77,94,120,150],"model":[79],"usually":[82],"expensive.":[83],"Even":[84],"worse,":[85],"if":[86],"weak":[88],"classifier":[90,116],"used,":[92],"cost":[95,151],"significantly":[98],"increased.":[99],"paper,":[102],"we":[103,127],"propose":[104],"an":[105,129],"unsupervised":[106],"algorithm":[107],"determine":[109],"classifier.":[112],"The":[113,137],"process":[114],"initialization":[117],"requires":[118],"no":[119],"cost.":[121],"Then":[122],"on":[123],"our":[124,141],"proposed":[125],"algorithm,":[126],"present":[128],"sampling":[131],"method":[132],"selecting":[134],"examples.":[136],"experiments":[138],"show":[139],"approach":[142],"achieves":[143],"competitive":[144],"performance":[146],"much":[148],"less":[149],"than":[152],"other":[153],"approaches":[154],"learning.":[157]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}