{"id":"https://openalex.org/W1982538504","doi":"https://doi.org/10.1109/pccc.2013.6742785","title":"Scalable load balancing for mapreduce-based record linkage","display_name":"Scalable load balancing for mapreduce-based record linkage","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1982538504","doi":"https://doi.org/10.1109/pccc.2013.6742785","mag":"1982538504"},"language":"en","primary_location":{"id":"doi:10.1109/pccc.2013.6742785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pccc.2013.6742785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 32nd International Performance Computing and Communications Conference (IPCCC)","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/A5070936974","display_name":"Wei Yan","orcid":"https://orcid.org/0000-0003-3037-6300"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Yan","raw_affiliation_strings":["Dept. of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, USA","Dept. of Electr. Eng. & Comput. Sci., Vanderbilt Univ., Nashville, TN, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Dept. of Electr. Eng. & Comput. Sci., Vanderbilt Univ., Nashville, TN, USA#TAB#","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028544932","display_name":"Yuan Xue","orcid":"https://orcid.org/0000-0002-5390-9037"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xue","raw_affiliation_strings":["Dept. of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, USA","Dept. of Electr. Eng. & Comput. Sci., Vanderbilt Univ., Nashville, TN, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Dept. of Electr. Eng. & Comput. Sci., Vanderbilt Univ., Nashville, TN, USA#TAB#","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090647314","display_name":"Bradley Malin","orcid":"https://orcid.org/0000-0003-3040-5175"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bradley Malin","raw_affiliation_strings":["Dept. of Biomedical Informatics, Vanderbilt University, Nashville, TN, USA","Dept. of Biomed. Inf., Vanderbilt Univ., Nashville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Biomedical Informatics, Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Dept. of Biomed. Inf., Vanderbilt Univ., Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":2.8614,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.9010989,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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":0.9853000044822693,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9399999976158142,"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/computer-science","display_name":"Computer science","score":0.8787699937820435},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.798264741897583},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.7593432068824768},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6973819732666016},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.6894293427467346},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6275796890258789},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5977433919906616},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.5881022810935974},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5101921558380127},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42872804403305054},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4028010964393616},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38507315516471863},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2709285020828247},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20165443420410156},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09487086534500122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8787699937820435},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.798264741897583},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.7593432068824768},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6973819732666016},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.6894293427467346},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6275796890258789},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5977433919906616},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5881022810935974},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5101921558380127},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42872804403305054},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4028010964393616},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38507315516471863},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2709285020828247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20165443420410156},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09487086534500122},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":1,"locations":[{"id":"doi:10.1109/pccc.2013.6742785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pccc.2013.6742785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 32nd International Performance Computing and Communications Conference (IPCCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1981590391","https://openalex.org/W2031250218","https://openalex.org/W2034190452","https://openalex.org/W2043099794","https://openalex.org/W2052390074","https://openalex.org/W2058733945","https://openalex.org/W2058858139","https://openalex.org/W2061601738","https://openalex.org/W2070162726","https://openalex.org/W2073292498","https://openalex.org/W2073471108","https://openalex.org/W2080234606","https://openalex.org/W2102763740","https://openalex.org/W2105947650","https://openalex.org/W2107443258","https://openalex.org/W2108991785","https://openalex.org/W2120755171","https://openalex.org/W2140509629","https://openalex.org/W2151930506","https://openalex.org/W2173213060","https://openalex.org/W2397525010","https://openalex.org/W3146259567","https://openalex.org/W4230502578","https://openalex.org/W6667993270","https://openalex.org/W6676268515","https://openalex.org/W6712521661"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345","https://openalex.org/W1494563618","https://openalex.org/W2357022711"],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2],"introduced":[3],"load":[4,110,158],"balancing":[5,111,159],"schemes":[6],"that":[7,156],"are":[8],"aware":[9],"of":[10,28,54,77,90,149,172,181],"the":[11,25,29,88,120,147,163,173],"input":[12],"data":[13,16,20,48,64,121,143,183],"distribution":[14],"(i.e.,":[15],"profile)":[17],"to":[18,32,46,81,113,145,188],"mitigate":[19],"skew":[21,122],"and":[22,133,140,170],"fully":[23],"exploit":[24],"parallel":[26],"capability":[27],"MapReduce":[30],"framework":[31],"support":[33],"record":[34,60,126],"linkage.":[35,127],"However,":[36],"existing":[37],"solutions":[38],"face":[39],"a":[40,83,91,96,179],"significant":[41],"scalability":[42],"issue":[43],"when":[44],"applied":[45],"massive":[47],"sets":[49],"with":[50,125,138],"millions":[51],"or":[52],"billions":[53],"blocks":[55],"(a":[56],"basic":[57],"unit":[58],"in":[59,71,176],"linkage)":[61],"because":[62],"their":[63],"profiles":[65,117],"can":[66,161],"not":[67],"be":[68],"maintained":[69],"precisely":[70],"an":[72,130],"efficient":[73],"manner.":[74],"The":[75,152],"goal":[76],"this":[78],"paper":[79],"is":[80],"introduce":[82],"profiling":[84],"method":[85],"based":[86],"on":[87],"notion":[89],"sketch,":[92],"which":[93,185],"allows":[94],"for":[95,100],"compact":[97],"scalable":[98],"solution":[99],"maintaining":[101],"block":[102],"size":[103],"statistics.":[104],"In":[105],"addition,":[106],"we":[107],"propose":[108],"two":[109],"algorithms":[112,160],"work":[114],"over":[115],"sketch-based":[116],"while":[118],"solving":[119],"problem":[123],"associated":[124],"We":[128],"provide":[129],"analytical":[131],"analysis":[132],"extensive":[134],"experiments":[135],"(using":[136],"Hadoop),":[137],"real":[139],"controlled":[141],"synthetic":[142],"sets,":[144,184],"illustrate":[146],"effectiveness":[148],"our":[150,157],"solution.":[151],"experimental":[153],"results":[154],"show":[155],"decrease":[162],"overall":[164],"job":[165],"completion":[166],"time":[167],"by":[168],"71.56%":[169],"70.73%":[171],"default":[174],"settings":[175],"Hadoop":[177],"using":[178],"set":[180],"DBLP":[182],"have":[186],"2.5":[187],"50.4":[189],"million":[190],"records.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}