{"id":"https://openalex.org/W2973207699","doi":"https://doi.org/10.1080/10618600.2020.1825451","title":"d-blink: Distributed End-to-End Bayesian Entity Resolution","display_name":"d-blink: Distributed End-to-End Bayesian Entity Resolution","publication_year":2020,"publication_date":"2020-09-23","ids":{"openalex":"https://openalex.org/W2973207699","doi":"https://doi.org/10.1080/10618600.2020.1825451","mag":"2973207699"},"language":"en","primary_location":{"id":"doi:10.1080/10618600.2020.1825451","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2020.1825451","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.06039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Neil G. Marchant","orcid":"https://orcid.org/0000-0001-5713-4235"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Neil G. Marchant","raw_affiliation_strings":["School of Computing and Information Systems, University of Melbourne ,  Parkville ,  VIC ,  Australia ;"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, University of Melbourne ,  Parkville ,  VIC ,  Australia ;","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andee Kaplan","orcid":"https://orcid.org/0000-0002-2940-889X"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andee Kaplan","raw_affiliation_strings":["Department of Statistics, Colorado State University ,  Fort Collins ,  CO ;"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Colorado State University ,  Fort Collins ,  CO ;","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daniel N. Elazar","orcid":null},"institutions":[{"id":"https://openalex.org/I1324605556","display_name":"Australian Bureau of Statistics","ror":"https://ror.org/00ve6e186","country_code":"AU","type":"government","lineage":["https://openalex.org/I1280568170","https://openalex.org/I1324605556","https://openalex.org/I2801453606"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Daniel N. Elazar","raw_affiliation_strings":["Methodology Division, Australian Bureau of Statistics ,  Belconnen ,  ACT ,  Australia ;"],"affiliations":[{"raw_affiliation_string":"Methodology Division, Australian Bureau of Statistics ,  Belconnen ,  ACT ,  Australia ;","institution_ids":["https://openalex.org/I1324605556"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Benjamin I. P. Rubinstein","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Benjamin I. P. Rubinstein","raw_affiliation_strings":["School of Computing and Information Systems, University of Melbourne ,  Parkville ,  VIC ,  Australia ;"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, University of Melbourne ,  Parkville ,  VIC ,  Australia ;","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":null,"display_name":"Rebecca C. Steorts","orcid":null},"institutions":[{"id":"https://openalex.org/I1333512998","display_name":"United States Census Bureau","ror":"https://ror.org/01qn7cs15","country_code":"US","type":"government","lineage":["https://openalex.org/I1333512998","https://openalex.org/I1343035065"]},{"id":"https://openalex.org/I1343558604","display_name":"Statistical and Applied Mathematical Sciences Institute","ror":"https://ror.org/01shctp43","country_code":"US","type":"facility","lineage":["https://openalex.org/I1311060795","https://openalex.org/I1343558604"]},{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rebecca C. Steorts","raw_affiliation_strings":["Department of Statistical Science and Computer Science, Duke University ,  Durham ,  NC ;","Principal Mathematical Statistician, United States Census Bureau (DRB #: CBDRB-FY20-309)"],"affiliations":[{"raw_affiliation_string":"Department of Statistical Science and Computer Science, Duke University ,  Durham ,  NC ;","institution_ids":["https://openalex.org/I1343558604","https://openalex.org/I170897317"]},{"raw_affiliation_string":"Principal Mathematical Statistician, United States Census Bureau (DRB #: CBDRB-FY20-309)","institution_ids":["https://openalex.org/I1333512998"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":1.486,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.83393936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"30","issue":"2","first_page":"406","last_page":"421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9952999949455261,"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":0.9952999949455261,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.0010999999940395355,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.0006000000284984708,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5870000123977661},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.5691999793052673},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.534600019454956},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49549999833106995},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4586000144481659},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.3894999921321869},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3596999943256378},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.3578999936580658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257999777793884},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5870000123977661},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.5691999793052673},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4740000069141388},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4586000144481659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436599999666214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4350000023841858},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.33070001006126404},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C71983512","wikidata":"https://www.wikidata.org/wiki/Q7915687","display_name":"Variable-order Bayesian network","level":4,"score":0.3046000003814697},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.26589998602867126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/10618600.2020.1825451","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2020.1825451","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1909.06039","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.06039","pdf_url":"https://arxiv.org/pdf/1909.06039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.06039","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.06039","pdf_url":"https://arxiv.org/pdf/1909.06039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311212","display_name":"National Bureau of Statistics of China","ror":"https://ror.org/008zm7t63"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W1715327985","https://openalex.org/W1724849505","https://openalex.org/W1907304379","https://openalex.org/W1964786778","https://openalex.org/W1981519674","https://openalex.org/W1989692914","https://openalex.org/W1993637408","https://openalex.org/W2017353792","https://openalex.org/W2024668293","https://openalex.org/W2031250218","https://openalex.org/W2035756456","https://openalex.org/W2041439319","https://openalex.org/W2041517243","https://openalex.org/W2047464260","https://openalex.org/W2052390074","https://openalex.org/W2053870252","https://openalex.org/W2056748234","https://openalex.org/W2072096853","https://openalex.org/W2073471108","https://openalex.org/W2100231460","https://openalex.org/W2105929850","https://openalex.org/W2107966677","https://openalex.org/W2116940697","https://openalex.org/W2128286266","https://openalex.org/W2156279557","https://openalex.org/W2162021827","https://openalex.org/W2164455818","https://openalex.org/W2164456230","https://openalex.org/W2165558283","https://openalex.org/W2233560226","https://openalex.org/W2261631147","https://openalex.org/W2272596129","https://openalex.org/W2323506184","https://openalex.org/W2399361902","https://openalex.org/W2480680997","https://openalex.org/W2612177096","https://openalex.org/W2794286494","https://openalex.org/W2798649495","https://openalex.org/W2908287046","https://openalex.org/W2920239148","https://openalex.org/W2946587887","https://openalex.org/W2962777160","https://openalex.org/W2962997929","https://openalex.org/W2963313478","https://openalex.org/W3096011758","https://openalex.org/W6600144256","https://openalex.org/W6633667658","https://openalex.org/W6744880469","https://openalex.org/W6781752065"],"related_works":[],"abstract_inverted_index":{"Entity":[0],"resolution":[1],"(ER;":[2],"also":[3],"known":[4],"as":[5,62],"record":[6],"linkage":[7],"or":[8,115],"de-duplication)":[9],"is":[10],"the":[11,19,32,69,80,86,97,145,189,193],"process":[12],"of":[13,21,34,50,71,85,144,197],"merging":[14],"noisy":[15],"databases,":[16],"often":[17],"in":[18,27,60,68,96],"absence":[20],"unique":[22],"identifiers.":[23],"A":[24],"major":[25],"advancement":[26],"ER":[28,122],"methodology":[29],"has":[30],"been":[31],"application":[33],"Bayesian":[35,109,113],"generative":[36],"models,":[37],"which":[38,117],"provide":[39],"a":[40,89,104,142,152,163,185],"natural":[41],"framework":[42],"for":[43,107,154,176,202],"inferring":[44],"latent":[45],"entities":[46,146],"with":[47,169],"rigorous":[48],"quantification":[49],"uncertainty.":[51],"Despite":[52],"these":[53],"advantages,":[54],"existing":[55],"models":[56],"are":[57,205],"severely":[58],"limited":[59],"practice,":[61],"standard":[63],"inference":[64],"algorithms":[65,175],"scale":[66],"quadratically":[67],"number":[70],"records.":[72],"While":[73],"scaling":[74],"can":[75],"be":[76],"managed":[77],"by":[78],"fitting":[79],"model":[81,106],"on":[82,130,159,182,188],"separate":[83],"blocks":[84,157],"data,":[87],"such":[88],"na\u00efve":[90],"approach":[91,128],"may":[92],"induce":[93],"significant":[94],"error":[95],"posterior.":[98],"In":[99],"this":[100,203],"article,":[101],"we":[102],"propose":[103],"principled":[105],"scalable":[108],"ER,":[110],"called":[111],"\u201cdistributed":[112],"linkage\u201d":[114],"d-blink,":[116],"jointly":[118],"performs":[119],"blocking":[120],"and":[121,147,172,195],"without":[123],"compromising":[124],"posterior":[125],"correctness.":[126],"Our":[127],"relies":[129],"several":[131],"key":[132],"ideas,":[133],"including:":[134],"(i)":[135],"an":[136],"auxiliary":[137],"variable":[138],"representation":[139],"that":[140],"induces":[141],"partition":[143],"records":[148],"into":[149],"blocks;":[150],"(ii)":[151],"method":[153],"constructing":[155],"well-balanced":[156],"based":[158],"k-d":[160],"trees;":[161],"(iii)":[162],"distributed":[164],"partially":[165],"collapsed":[166],"Gibbs":[167,178],"sampler":[168],"improved":[170],"mixing;":[171],"(iv)":[173],"fast":[174],"performing":[177],"updates.":[179],"Empirical":[180],"studies":[181],"six":[183],"datasets\u2014including":[184],"case":[186],"study":[187],"2010":[190],"Decennial":[191],"Census\u2014demonstrate":[192],"scalability":[194],"effectiveness":[196],"our":[198],"approach.":[199],"Supplementary":[200],"materials":[201],"article":[204],"available":[206],"online.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2019-09-19T00:00:00"}