{"id":"https://openalex.org/W2111116800","doi":"https://doi.org/10.1109/icdm.2006.13","title":"Adaptive Blocking: Learning to Scale Up Record Linkage","display_name":"Adaptive Blocking: Learning to Scale Up Record Linkage","publication_year":2006,"publication_date":"2006-12-01","ids":{"openalex":"https://openalex.org/W2111116800","doi":"https://doi.org/10.1109/icdm.2006.13","mag":"2111116800"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2006.13","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2006.13","pdf_url":null,"source":{"id":"https://openalex.org/S4210214883","display_name":"Proceedings","issn_l":"1550-4786","issn":["1550-4786","2374-8486"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sixth International Conference on Data Mining (ICDM'06)","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/A5043706888","display_name":"Mikhail Bilenko","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mikhail Bilenko","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA","Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Beena Kamath","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Beena Kamath","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA","Google, Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008715111","display_name":"Raymond J. Mooney","orcid":"https://orcid.org/0000-0002-4504-0490"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raymond Mooney","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","Univ. of Texas at Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Univ. of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043706888"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":10.9323,"has_fulltext":false,"cited_by_count":232,"citation_normalized_percentile":{"value":0.98483016,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9847000241279602,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.98089998960495,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7209933400154114},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.6391355395317078},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.62856125831604},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.575934648513794},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5369956493377686},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.49482887983322144},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4578283429145813},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4351937174797058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38080844283103943},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3522668480873108},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29164278507232666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17067599296569824},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07897800207138062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209933400154114},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.6391355395317078},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.62856125831604},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.575934648513794},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5369956493377686},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.49482887983322144},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4578283429145813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4351937174797058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38080844283103943},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3522668480873108},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29164278507232666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17067599296569824},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07897800207138062},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdm.2006.13","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2006.13","pdf_url":null,"source":{"id":"https://openalex.org/S4210214883","display_name":"Proceedings","issn_l":"1550-4786","issn":["1550-4786","2374-8486"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sixth International Conference on Data Mining (ICDM'06)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.2626","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.2626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/mbilenko/papers/06-icdm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.85.949","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ra.ethz.ch/CDstore/www2006/iiweb2006.cs.uiuc.edu/20.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W154872207","https://openalex.org/W1536860849","https://openalex.org/W1540269031","https://openalex.org/W1560724230","https://openalex.org/W1569123402","https://openalex.org/W1606801372","https://openalex.org/W1670263352","https://openalex.org/W1689241477","https://openalex.org/W1742677423","https://openalex.org/W1920916604","https://openalex.org/W1981873012","https://openalex.org/W1992419399","https://openalex.org/W1997321932","https://openalex.org/W2024505010","https://openalex.org/W2024770506","https://openalex.org/W2034190452","https://openalex.org/W2036216970","https://openalex.org/W2046020929","https://openalex.org/W2058755145","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2085099553","https://openalex.org/W2102350406","https://openalex.org/W2105423800","https://openalex.org/W2111625757","https://openalex.org/W2112912553","https://openalex.org/W2127674618","https://openalex.org/W2133236963","https://openalex.org/W2147717514","https://openalex.org/W2148572968","https://openalex.org/W2150546140","https://openalex.org/W2154785834","https://openalex.org/W2157054705","https://openalex.org/W2159481891","https://openalex.org/W2161600801","https://openalex.org/W2164456230","https://openalex.org/W2165874743","https://openalex.org/W2168190036","https://openalex.org/W2170605888","https://openalex.org/W2171574281","https://openalex.org/W3144619878","https://openalex.org/W4214588406","https://openalex.org/W4230502578","https://openalex.org/W4254734767","https://openalex.org/W6632038546","https://openalex.org/W6633966005","https://openalex.org/W6636380351","https://openalex.org/W6637351985","https://openalex.org/W6637772234","https://openalex.org/W6656333955","https://openalex.org/W6676669657","https://openalex.org/W6679396267","https://openalex.org/W6683373780","https://openalex.org/W6683628169","https://openalex.org/W6684578312","https://openalex.org/W6685232391"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2942366970","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W2392835431","https://openalex.org/W4360593462","https://openalex.org/W2023397165"],"abstract_inverted_index":{"Many":[0],"data":[1],"mining":[2],"tasks":[3],"require":[4,88],"computing":[5,44],"similarity":[6,12,45,59,94],"between":[7,46],"pairs":[8,35,48,72,81],"of":[9,33,41,100,105,130,143],"objects.":[10],"Pairwise":[11],"computations":[13],"are":[14,121],"particularly":[15],"important":[16],"in":[17,24],"record":[18],"linkage":[19],"systems,":[20],"as":[21,23,82],"well":[22],"clustering":[25],"and":[26,51,57,123,134,151],"schema":[27],"mapping":[28],"algorithms.":[29],"Because":[30],"the":[31,39,42,79,144],"number":[32],"object":[34,71],"grows":[36],"quadratically":[37],"with":[38],"size":[40],"dataset,":[43],"all":[47],"is":[49,147],"impractical":[50],"becomes":[52],"prohibitive":[53],"for":[54,73,115,138],"large":[55],"datasets":[56],"complex":[58],"functions.":[60],"Blocking":[61],"methods":[62,87],"alleviate":[63],"this":[64,108],"problem":[65],"by":[66,103],"efficiently":[67],"selecting":[68,97],"approximately":[69],"similar":[70],"subsequent":[74],"distance":[75],"computations,":[76],"leaving":[77],"out":[78],"remaining":[80],"dissimilar.":[83],"Previously":[84],"proposed":[85,145],"blocking":[86,118,132,164],"manually":[89],"constructing":[90],"an":[91,112],"index-":[92],"based":[93],"function":[95],"or":[96],"a":[98],"set":[99],"predicates,":[101],"followed":[102],"hand-tuning":[104],"parameters.":[106],"In":[107],"paper,":[109],"we":[110],"introduce":[111],"adaptive":[113],"framework":[114],"automatically":[116],"learning":[117,136],"functions":[119,133],"that":[120],"efficient":[122],"accurate.":[124],"We":[125],"describe":[126],"two":[127],"predicate-based":[128],"formulations":[129],"learnable":[131],"provide":[135],"algorithms":[137],"training":[139],"them.":[140],"The":[141],"effectiveness":[142],"techniques":[146],"demonstrated":[148],"on":[149,154],"real":[150],"simulated":[152],"datasets,":[153],"which":[155],"they":[156],"prove":[157],"to":[158],"be":[159],"more":[160],"accurate":[161],"than":[162],"non-adaptive":[163],"methods.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":12}],"updated_date":"2026-04-27T08:22:11.395708","created_date":"2025-10-10T00:00:00"}