{"id":"https://openalex.org/W2147299132","doi":"https://doi.org/10.1109/icde.2011.5767835","title":"Efficient SPectrAl Neighborhood blocking for entity resolution","display_name":"Efficient SPectrAl Neighborhood blocking for entity resolution","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2147299132","doi":"https://doi.org/10.1109/icde.2011.5767835","mag":"2147299132"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2011.5767835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2011.5767835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 27th International Conference on Data Engineering","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/A5045189040","display_name":"Liangcai Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liangcai Shu","raw_affiliation_strings":["Department of Computer Science, SUNY at Binghamton, Binghamton, NY, USA","Dept. of Computer Science, SUNY at Binghamton, PO BOX 6000, NY 13902, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, SUNY at Binghamton, Binghamton, NY, USA","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"Dept. of Computer Science, SUNY at Binghamton, PO BOX 6000, NY 13902, USA","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085800638","display_name":"Aiyou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1322087612","display_name":"Alcatel Lucent (Germany)","ror":"https://ror.org/00c5mwp75","country_code":"DE","type":"company","lineage":["https://openalex.org/I1322087612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Aiyou Chen","raw_affiliation_strings":["Bell Laboratories, Alcatel-Lucent, Murry Hill, NJ, USA","Bell Labs, Alcatel-Lucent, 700 Mountain Ave, Murry Hill, NJ 07974, USA"],"affiliations":[{"raw_affiliation_string":"Bell Laboratories, Alcatel-Lucent, Murry Hill, NJ, USA","institution_ids":["https://openalex.org/I1322087612"]},{"raw_affiliation_string":"Bell Labs, Alcatel-Lucent, 700 Mountain Ave, Murry Hill, NJ 07974, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101713518","display_name":"Ming Xiong","orcid":"https://orcid.org/0000-0003-2366-4160"},"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":"Ming Xiong","raw_affiliation_strings":["Google, Inc., New York, NY, USA","Google, Inc., 76 9th Avenue, New York, 10011, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc., 76 9th Avenue, New York, 10011, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101960531","display_name":"Weiyi Meng","orcid":"https://orcid.org/0000-0002-7246-2058"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiyi Meng","raw_affiliation_strings":["Department of Computer Science, SUNY at Binghamton, Binghamton, NY, USA","Dept. of Computer Science, SUNY at Binghamton, PO BOX 6000, NY 13902, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, SUNY at Binghamton, Binghamton, NY, USA","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"Dept. of Computer Science, SUNY at Binghamton, PO BOX 6000, NY 13902, USA","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045189040"],"corresponding_institution_ids":["https://openalex.org/I123946342"],"apc_list":null,"apc_paid":null,"fwci":3.8089,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.9325298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"14","issue":null,"first_page":"1067","last_page":"1078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9912999868392944,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9898999929428101,"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":0.8112584352493286},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7463378310203552},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6913500428199768},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.6478891372680664},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.6155815124511719},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6046212315559387},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.564626932144165},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5484264492988586},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.5249245762825012},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.46658971905708313},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4584372639656067},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35470306873321533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34964093565940857},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21559900045394897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10427349805831909}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8112584352493286},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7463378310203552},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6913500428199768},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.6478891372680664},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.6155815124511719},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6046212315559387},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.564626932144165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5484264492988586},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.5249245762825012},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.46658971905708313},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4584372639656067},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35470306873321533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34964093565940857},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21559900045394897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10427349805831909},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icde.2011.5767835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2011.5767835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 27th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.4806","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.4806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.binghamton.edu/~meng/pub.d/ICDE11_conf_full_065_update.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.3943","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.3943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/36940.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.4399999976158142,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332603","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W73389528","https://openalex.org/W177885090","https://openalex.org/W1532325895","https://openalex.org/W1536860849","https://openalex.org/W1612155886","https://openalex.org/W1647671624","https://openalex.org/W1700279323","https://openalex.org/W1768893245","https://openalex.org/W1920916604","https://openalex.org/W1964786778","https://openalex.org/W1982806687","https://openalex.org/W2002276939","https://openalex.org/W2014712792","https://openalex.org/W2029097226","https://openalex.org/W2030116982","https://openalex.org/W2036216970","https://openalex.org/W2043481183","https://openalex.org/W2052390074","https://openalex.org/W2055405704","https://openalex.org/W2056826404","https://openalex.org/W2064274783","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2095293504","https://openalex.org/W2097820631","https://openalex.org/W2105484782","https://openalex.org/W2108991785","https://openalex.org/W2116544254","https://openalex.org/W2116810533","https://openalex.org/W2117974736","https://openalex.org/W2121947440","https://openalex.org/W2134370969","https://openalex.org/W2139230981","https://openalex.org/W2147152072","https://openalex.org/W2148524305","https://openalex.org/W2159481891","https://openalex.org/W2164456230","https://openalex.org/W2165612380","https://openalex.org/W2165874743","https://openalex.org/W2167055514","https://openalex.org/W2171574281","https://openalex.org/W2572321817","https://openalex.org/W2798909945","https://openalex.org/W3146259567","https://openalex.org/W4213009331","https://openalex.org/W4230502578","https://openalex.org/W4252421678","https://openalex.org/W4254734767","https://openalex.org/W6601892241","https://openalex.org/W6607222731","https://openalex.org/W6636915900","https://openalex.org/W6674539747","https://openalex.org/W6683373780","https://openalex.org/W6684578312","https://openalex.org/W6685232391"],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W3130054399","https://openalex.org/W4301062032","https://openalex.org/W2343500026","https://openalex.org/W2319837024","https://openalex.org/W2390627310","https://openalex.org/W2033159440","https://openalex.org/W2413664130","https://openalex.org/W2051731675"],"abstract_inverted_index":{"In":[0],"many":[1],"telecom":[2],"and":[3,42,67,96,193,201,214],"web":[4],"applications,":[5],"there":[6,48],"is":[7,64,199,212],"a":[8,50,59,103,114,150,176],"need":[9],"to":[10,57,65,76,216],"identify":[11,66],"whether":[12],"data":[13,55,72,92,195,220],"objects":[14,69],"in":[15,26,34,38,44,70,80,136,145,183,206],"the":[16,23,27,71,77,81,86,119,137,165,168,184],"same":[17,24,78],"source":[18],"or":[19],"different":[20],"sources":[21,56],"represent":[22,58],"entity":[25,79,87],"real-world.":[28],"This":[29],"problem":[30,89],"arises":[31],"for":[32,90,118],"subscribers":[33],"multiple":[35,54],"services,":[36],"customers":[37],"supply":[39],"chain":[40],"management,":[41],"users":[43],"social":[45],"networks":[46],"when":[47],"lacks":[49],"unique":[51],"identifier":[52],"across":[53],"real-world":[60,194],"entity.":[61],"Entity":[62],"resolution":[63,88],"discover":[68],"sets":[73,93],"that":[74,126,153,197],"refer":[75],"real":[82,127],"world.":[83],"We":[84,101,174],"investigate":[85],"large":[91,219],"where":[94],"efficient":[95,213],"scalable":[97,215],"solutions":[98],"are":[99,140],"needed.":[100],"propose":[102],"novel":[104,143],"unsupervised":[105],"blocking":[106,204],"algorithm,":[107],"namely":[108],"SPectrAl":[109],"Neighborhood":[110],"(SPAN),":[111],"which":[112,162],"constructs":[113],"fast":[115,151],"bipartition":[116,185],"tree":[117],"records":[120,135],"based":[121],"on":[122],"spectral":[123,155,170],"clustering":[124,156,171],"such":[125],"entities":[128],"can":[129],"be":[130],"identified":[131],"accurately":[132],"by":[133,180],"neighborhood":[134],"tree.":[138],"There":[139],"two":[141],"major":[142],"aspects":[144],"our":[146],"approach:":[147],"1)We":[148],"develop":[149],"algorithm":[152],"performs":[154],"without":[157],"computing":[158],"pairwise":[159],"similarities":[160],"explicitly,":[161],"dramatically":[163],"improves":[164],"scalability":[166],"of":[167,208],"standard":[169],"algorithm;":[172],"2)":[173],"utilize":[175],"stopping":[177],"criterion":[178],"specified":[179],"Newman-Girvan":[181],"modularity":[182],"process.":[186],"Our":[187],"experimental":[188],"results":[189],"with":[190,218],"both":[191],"synthetic":[192],"demonstrate":[196],"SPAN":[198],"robust":[200],"outperforms":[202],"other":[203],"algorithms":[205],"terms":[207],"accuracy":[209],"while":[210],"it":[211],"deal":[217],"sets.":[221]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}