{"id":"https://openalex.org/W2216499221","doi":"https://doi.org/10.1109/bigdata.2015.7363782","title":"Parallel meta-blocking: Realizing scalable entity resolution over large, heterogeneous data","display_name":"Parallel meta-blocking: Realizing scalable entity resolution over large, heterogeneous data","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2216499221","doi":"https://doi.org/10.1109/bigdata.2015.7363782","mag":"2216499221"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073440687","display_name":"Vasilis Efthymiou","orcid":"https://orcid.org/0000-0002-0683-030X"},"institutions":[{"id":"https://openalex.org/I4210121775","display_name":"FORTH Institute of Computer Science","ror":"https://ror.org/02tf48g55","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210121775","https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vasilis Efthymiou","raw_affiliation_strings":["ICS-FORTH, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICS-FORTH, Greece","institution_ids":["https://openalex.org/I4210121775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056976720","display_name":"George Papadakis","orcid":"https://orcid.org/0000-0002-7298-9431"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Papadakis","raw_affiliation_strings":["University of Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001091619","display_name":"George Papastefanatos","orcid":"https://orcid.org/0000-0002-9273-9843"},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Papastefanatos","raw_affiliation_strings":["Athena Research Center, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athena Research Center, Greece","institution_ids":["https://openalex.org/I4210156054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042740371","display_name":"Kostas Stefanidis","orcid":"https://orcid.org/0000-0003-1317-8062"},"institutions":[{"id":"https://openalex.org/I4210121775","display_name":"FORTH Institute of Computer Science","ror":"https://ror.org/02tf48g55","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210121775","https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Kostas Stefanidis","raw_affiliation_strings":["ICS-FORTH, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICS-FORTH, Greece","institution_ids":["https://openalex.org/I4210121775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053726723","display_name":"Themis Palpanas","orcid":"https://orcid.org/0000-0002-8031-0265"},"institutions":[{"id":"https://openalex.org/I110736937","display_name":"D\u00e9l\u00e9gation Paris 5","ror":"https://ror.org/02e0y6e06","country_code":"FR","type":"government","lineage":["https://openalex.org/I110736937","https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Themis Palpanas","raw_affiliation_strings":["Paris Descartes University, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paris Descartes University, France","institution_ids":["https://openalex.org/I110736937","https://openalex.org/I204730241"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"420"},"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9668999910354614,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9508000016212463,"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":0.8559345602989197},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.8390326499938965},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.70986008644104},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49630290269851685},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.49190711975097656},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4778158962726593},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.46581152081489563},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4597833752632141},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.42953264713287354},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34450334310531616},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16886606812477112},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10738193988800049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8559345602989197},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.8390326499938965},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.70986008644104},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49630290269851685},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.49190711975097656},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4778158962726593},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.46581152081489563},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4597833752632141},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.42953264713287354},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34450334310531616},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16886606812477112},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10738193988800049},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2015.7363782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.706.8761","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.706.8761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.ics.forth.gr/%7Ekstef/docs/bigdata15b.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1973734023","https://openalex.org/W1986017822","https://openalex.org/W2031250218","https://openalex.org/W2041439319","https://openalex.org/W2046020929","https://openalex.org/W2058733945","https://openalex.org/W2079649893","https://openalex.org/W2096742765","https://openalex.org/W2101654853","https://openalex.org/W2117974736","https://openalex.org/W2123561513","https://openalex.org/W2138105615","https://openalex.org/W2145908616","https://openalex.org/W2148019918","https://openalex.org/W2152502401","https://openalex.org/W2208310611","https://openalex.org/W2223011434","https://openalex.org/W2281536957","https://openalex.org/W2295151155","https://openalex.org/W2323506184","https://openalex.org/W2529367823","https://openalex.org/W6680062358","https://openalex.org/W6728303313"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W3138386522","https://openalex.org/W2499279132","https://openalex.org/W1966837078"],"abstract_inverted_index":{"Entity":[0],"resolution":[1],"constitutes":[2],"a":[3,76,91,126],"crucial":[4],"task":[5],"for":[6,158],"many":[7],"applications,":[8],"but":[9],"has":[10],"an":[11,108,154],"inherently":[12],"quadratic":[13],"complexity.":[14],"Typically,":[15],"it":[16,33,61],"scales":[17],"to":[18,35,62,164],"large":[19],"volumes":[20],"of":[21,100,120,148,167],"data":[22,121],"through":[23],"blocking:":[24],"similar":[25],"entities":[26,67],"are":[27],"clustered":[28],"into":[29],"blocks":[30,50,63],"so":[31],"that":[32,94,111,130],"suffices":[34],"perform":[36],"comparisons":[37,70],"only":[38],"within":[39],"each":[40],"block.":[41],"Meta-blocking":[42,56,85],"further":[43],"increases":[44],"efficiency":[45],"by":[46],"cleaning":[47],"the":[48,97,102,113,118,132,138,146,165],"overlapping":[49],"from":[51],"unnecessary":[52],"comparisons.":[53],"However,":[54],"even":[55],"can":[57],"be":[58],"time-consuming:":[59],"applying":[60],"with":[64,162],"7.4":[65],"million":[66],"and":[68,152],"2.21011":[69],"takes":[71],"almost":[72,155],"8":[73],"days":[74],"on":[75,87],"modern":[77],"high-end":[78],"server.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83],"parallelize":[84],"based":[86],"MapReduce.":[88],"We":[89,105,123],"propose":[90],"simple":[92],"strategy":[93,110,151],"explicitly":[95],"creates":[96,112],"core":[98],"concept":[99],"Meta-blocking,":[101],"blocking":[103,114],"graph.":[104],"then":[106],"describe":[107],"advanced":[109,150],"graph":[115],"implicitly,":[116],"reducing":[117],"overhead":[119],"exchange.":[122],"also":[124],"introduce":[125],"load":[127],"balancing":[128],"algorithm":[129],"distributes":[131],"computationally":[133],"intensive":[134],"workload":[135],"evenly":[136],"among":[137],"available":[139,168],"compute":[140],"nodes.":[141,169],"Our":[142],"experimental":[143],"analysis":[144],"verifies":[145],"superiority":[147],"our":[149],"demonstrates":[153],"linear":[156],"speedup":[157],"all":[159],"meta-blocking":[160],"techniques":[161],"respect":[163],"number":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}