{"id":"https://openalex.org/W2080131844","doi":"https://doi.org/10.1109/tpds.2014.2350972","title":"LIBRA: Lightweight Data Skew Mitigation in MapReduce","display_name":"LIBRA: Lightweight Data Skew Mitigation in MapReduce","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W2080131844","doi":"https://doi.org/10.1109/tpds.2014.2350972","mag":"2080131844"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2014.2350972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2350972","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5100340205","display_name":"Qi Chen","orcid":"https://orcid.org/0000-0003-3559-8914"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Chen","raw_affiliation_strings":["Department of Computer Science at Peking University, Beijing, China","[Department of Computer Science at Peking University, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science at Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"[Department of Computer Science at Peking University, Beijing, China]","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040820855","display_name":"Jinyu Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyu Yao","raw_affiliation_strings":["Department of Computer Science at Peking University, Beijing, China","[Department of Computer Science at Peking University, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science at Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"[Department of Computer Science at Peking University, Beijing, China]","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102979232","display_name":"Zhen Xiao","orcid":"https://orcid.org/0000-0002-6784-9709"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xiao","raw_affiliation_strings":["Department of Computer Science at Peking University, Beijing, China","[Department of Computer Science at Peking University, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science at Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"[Department of Computer Science at Peking University, Beijing, China]","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100340205"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":26.2493,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.99438362,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":"9","first_page":"2520","last_page":"2533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8856977224349976},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.8196845054626465},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6672886610031128},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5907397866249084},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5512861609458923},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5233951210975647},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.5010130405426025},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4835043251514435},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4779353439807892},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.41015535593032837},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.30538326501846313},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18236762285232544},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.10136404633522034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8856977224349976},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.8196845054626465},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6672886610031128},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5907397866249084},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5512861609458923},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5233951210975647},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.5010130405426025},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4835043251514435},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4779353439807892},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41015535593032837},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30538326501846313},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18236762285232544},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.10136404633522034},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2014.2350972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2350972","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7868600614","display_name":"\u591a\u6838\u73af\u5883\u4e0b\u865a\u62df\u673a\u5728\u7ebf\u786e\u5b9a\u6027\u91cd\u6f14\u6280\u672f\u7814\u7a76","funder_award_id":"61170056","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1487093789","https://openalex.org/W1520750340","https://openalex.org/W1597532222","https://openalex.org/W1861377444","https://openalex.org/W1888294891","https://openalex.org/W2017540033","https://openalex.org/W2024680396","https://openalex.org/W2040722314","https://openalex.org/W2061601738","https://openalex.org/W2091842814","https://openalex.org/W2098935637","https://openalex.org/W2100830825","https://openalex.org/W2110104287","https://openalex.org/W2120755171","https://openalex.org/W2121762798","https://openalex.org/W2140509629","https://openalex.org/W2141267666","https://openalex.org/W2142031898","https://openalex.org/W2143108641","https://openalex.org/W2144628693","https://openalex.org/W2146223937","https://openalex.org/W2151487638","https://openalex.org/W2156441202","https://openalex.org/W2165769837","https://openalex.org/W2173213060","https://openalex.org/W2199389590","https://openalex.org/W2399133307","https://openalex.org/W2978655370","https://openalex.org/W4250212406","https://openalex.org/W6629167675","https://openalex.org/W6631168969","https://openalex.org/W6635650928","https://openalex.org/W6639193275","https://openalex.org/W6639518697","https://openalex.org/W6676421412"],"related_works":["https://openalex.org/W4290802965","https://openalex.org/W4390608645","https://openalex.org/W97789383","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4233347783","https://openalex.org/W2163482186"],"abstract_inverted_index":{"MapReduce":[0,14,64],"is":[1,16,191,200],"an":[2,93],"effective":[3],"tool":[4],"for":[5],"parallel":[6],"data":[7,17,25,57,79,110,120],"processing.":[8,125],"One":[9],"significant":[10],"issue":[11],"in":[12,21,208],"practical":[13],"applications":[15,198,228],"skew:":[18],"the":[19,22,56,61,77,82,85,88,105,108,118,122,128,137,156,166,170,175,178,183,186,203,223],"imbalance":[20],"amount":[23],"of":[24,63,76,107,117,146,158,169,177,197,225,234],"assigned":[26],"to":[27,34,38,54,104,131,193,202,231],"each":[28],"task.":[29],"This":[30,47],"causes":[31],"some":[32,226],"tasks":[33,130,141,148,188],"take":[35],"much":[36],"longer":[37],"finish":[39],"than":[40],"others":[41],"and":[42,87,165,199,210,219],"can":[43,98,220],"significantly":[44],"impact":[45],"performance.":[46],"paper":[48],"presents":[49],"LIBRA,":[50],"a":[51,100,114,143,194,232],"lightweight":[52],"strategy":[53],"address":[55],"skew":[58],"problem":[59],"among":[60,185],"reducers":[62],"applications.":[65],"Unlike":[66],"previous":[67],"work,":[68],"LIBRA":[69,190,207,215],"does":[70],"not":[71],"require":[72],"any":[73],"pre-run":[74],"sampling":[75,95,112],"input":[78],"or":[80],"prevent":[81],"overlap":[83],"between":[84],"map":[86,124,140,147],"reduce":[89,129,187],"stages.":[90],"It":[91,126,154,173],"uses":[92],"innovative":[94],"method":[96],"which":[97,149],"achieve":[99],"highly":[101],"accurate":[102],"approximation":[103],"distribution":[106],"intermediate":[109,119],"by":[111,229],"only":[113],"small":[115,144],"fraction":[116,145],"during":[121],"normal":[123],"allows":[127],"start":[132],"copying":[133],"as":[134,136],"soon":[135],"chosen":[138],"sample":[139],"(only":[142],"are":[150],"issued":[151],"first)":[152],"complete.":[153],"supports":[155],"split":[157],"large":[159],"keys":[160],"when":[161,181],"application":[162],"semantics":[163],"permit":[164],"total":[167],"order":[168],"output":[171],"data.":[172],"considers":[174],"heterogeneity":[176],"computing":[179],"resources":[180],"balancing":[182],"load":[184],"appropriately.":[189],"applicable":[192],"wide":[195],"range":[196],"transparent":[201],"users.":[204],"We":[205],"implement":[206],"Hadoop":[209],"our":[211],"experiments":[212],"show":[213],"that":[214],"has":[216],"negligible":[217],"overhead":[218],"speed":[221],"up":[222,230],"execution":[224],"popular":[227],"factor":[233],"4.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":3}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}