{"id":"https://openalex.org/W4206595948","doi":"https://doi.org/10.1109/access.2021.3139987","title":"Progressive Entity Matching via Cost Benefit Analysis","display_name":"Progressive Entity Matching via Cost Benefit Analysis","publication_year":2021,"publication_date":"2021-12-31","ids":{"openalex":"https://openalex.org/W4206595948","doi":"https://doi.org/10.1109/access.2021.3139987"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3139987","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3139987","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09667382.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09667382.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100771483","display_name":"Chenchen Sun","orcid":"https://orcid.org/0000-0002-9990-0425"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]},{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenchen Sun","raw_affiliation_strings":["Key Laboratory of Computer Vision and System (Ministry of Education), Tianjin University of Technology, Tianjin, China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-9990-0425","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer Vision and System (Ministry of Education), Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047030626","display_name":"Zhijiang Hou","orcid":"https://orcid.org/0000-0001-8990-664X"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijiang Hou","raw_affiliation_strings":["Library, Tianjin University of Technology, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Library, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015251362","display_name":"Derong Shen","orcid":"https://orcid.org/0000-0003-0310-6372"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Derong Shen","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102979521","display_name":"Tiezheng Nie","orcid":"https://orcid.org/0000-0002-0166-1324"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiezheng Nie","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.25064974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"10","issue":null,"first_page":"3979","last_page":"3989"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9832000136375427,"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/T11106","display_name":"Data Management and Algorithms","score":0.9824000000953674,"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":0.8571837544441223},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6555877923965454},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.6279870867729187},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5939894914627075},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5754384398460388},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5652764439582825},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5488229990005493},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.5009043216705322},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4931644797325134},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.45969927310943604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21332275867462158},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21061912178993225},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.14583653211593628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8571837544441223},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6555877923965454},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.6279870867729187},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5939894914627075},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5754384398460388},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5652764439582825},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5488229990005493},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.5009043216705322},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4931644797325134},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.45969927310943604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21332275867462158},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21061912178993225},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.14583653211593628},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3139987","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3139987","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09667382.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b56c7db254a64f368cb3e4297cf8f6e4","is_oa":true,"landing_page_url":"https://doaj.org/article/b56c7db254a64f368cb3e4297cf8f6e4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 3979-3989 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3139987","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3139987","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09667382.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1230797840","display_name":"\u5177\u6709\u53cd\u9988\u673a\u5236\u7684\u79d1\u6280\u8bba\u6587\u5185\u5bb9\u8d28\u91cf\u53ef\u8ba1\u7b97\u5316\u8bc4\u4ef7\u6a21\u578b\u7814\u7a76","funder_award_id":"71804123","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1425812762","display_name":null,"funder_award_id":"62172082","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3064489609","display_name":null,"funder_award_id":"62002262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5505926156","display_name":"\u57fa\u4e8e\u7fa4\u7ec4\u751f\u6210\u673a\u7406\u7684\u53ef\u89e3\u91ca\u7fa4\u7ec4\u63a8\u8350\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072084","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7932691611","display_name":"\u9762\u5411\u5927\u6570\u636e\u878d\u5408\u7684\u533a\u5757\u94fe\u6570\u636e\u7ba1\u7406\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4206595948.pdf","grobid_xml":"https://content.openalex.org/works/W4206595948.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1981590391","https://openalex.org/W2029554959","https://openalex.org/W2031250218","https://openalex.org/W2035615211","https://openalex.org/W2045492613","https://openalex.org/W2069897123","https://openalex.org/W2106521941","https://openalex.org/W2108087318","https://openalex.org/W2140190241","https://openalex.org/W2156293131","https://openalex.org/W2168440643","https://openalex.org/W2237063244","https://openalex.org/W2243458913","https://openalex.org/W2615445186","https://openalex.org/W2798649495","https://openalex.org/W2946741276","https://openalex.org/W2952367660","https://openalex.org/W2963753024","https://openalex.org/W3029621839","https://openalex.org/W3032015135","https://openalex.org/W3137039868","https://openalex.org/W3152703111","https://openalex.org/W4214544795","https://openalex.org/W6611560470","https://openalex.org/W6749221066","https://openalex.org/W6775593301"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W4390608645"],"abstract_inverted_index":{"Entity":[0],"matching":[1],"(EM)":[2],"is":[3,11,144,154,172],"a":[4,12,78,101,168],"fundamental":[5],"problem":[6],"in":[7,16,46,100],"data":[8,18,25,29,88,98,136,177],"preprocessing,":[9],"and":[10,20,33,94,135,148,151,195],"long":[13],"running":[14],"topic":[15],"big":[17,24],"analytics":[19],"mining":[21],"communities.":[22],"In":[23],"era,":[26],"(nearly)":[27],"real-time":[28],"applications":[30],"become":[31],"popular,":[32],"call":[34],"for":[35,104,178],"progressive":[36,51,83,106],"EM,":[37],"which":[38,86],"produces":[39],"as":[40,44],"many":[41],"match":[42],"pairs":[43],"possible":[45],"very":[47],"limited":[48],"time.":[49],"Previous":[50],"EM":[52,84],"focus":[53],"on":[54,111],"memory":[55],"based":[56,60,82,110],"solutions,":[57],"but":[58],"disk":[59],"solutions":[61],"are":[62,117,128,138],"necessary":[63],"when":[64],"dirty":[65],"datasets":[66,190],"cannot":[67],"be":[68],"fully":[69],"loaded":[70],"into":[71],"memory.":[72],"To":[73],"this":[74],"end,":[75],"we":[76,184],"propose":[77],"cost":[79,142,165],"benefit":[80,152,166],"analysis":[81],"approach,":[85,194],"partitions":[87,99,137],"according":[89],"to":[90,131,174,191],"coarse":[91],"clustering":[92],"results":[93],"then":[95],"iteratively":[96],"schedules":[97],"greedy":[102,169],"way":[103],"high":[105,179],"resolution.":[107],"At":[108],"first,":[109],"estimated":[112],"record":[113,122],"pair":[114],"similarities,":[115],"records":[116],"fast":[118],"coarsely":[119],"clustered;":[120],"then,":[121],"clusters":[123],"with":[124,146,156],"near":[125],"average":[126],"similarities":[127],"greedily":[129],"distributed":[130],"the":[132,161,164],"same":[133],"partitions,":[134],"cached.":[139],"After":[140],"that,":[141],"model":[143,153],"defined":[145,155],"time":[147],"space":[149],"constrains,":[150],"expected":[157],"resolution":[158],"results.":[159],"On":[160],"basis":[162],"of":[163,181],"model,":[167],"approximate":[170],"method":[171],"proposed":[173],"effectively":[175],"schedule":[176],"progressiveness":[180],"EM.":[182],"Finally,":[183],"implement":[185],"extensive":[186],"experiments":[187],"over":[188,199],"several":[189],"evaluate":[192],"our":[193],"show":[196],"its":[197],"advantages":[198],"existing":[200],"works.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}