{"id":"https://openalex.org/W2073292498","doi":"https://doi.org/10.1109/bigdata.2013.6691568","title":"Scalable and robust key group size estimation for reducer load balancing in MapReduce","display_name":"Scalable and robust key group size estimation for reducer load balancing in MapReduce","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2073292498","doi":"https://doi.org/10.1109/bigdata.2013.6691568","mag":"2073292498"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","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/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":true,"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#"],"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#"],"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"],"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":3,"corresponding_author_ids":["https://openalex.org/A5070936974"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":9.7075,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.97646402,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"162"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8494958281517029},{"id":"https://openalex.org/keywords/reducer","display_name":"Reducer","score":0.7731783986091614},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.7349622249603271},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.6900732517242432},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6620671153068542},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6388656497001648},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5457985401153564},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5312813520431519},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5227770209312439},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.4521803855895996},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24800431728363037},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1463889479637146},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0795290470123291}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8494958281517029},{"id":"https://openalex.org/C2776985865","wikidata":"https://www.wikidata.org/wiki/Q26820931","display_name":"Reducer","level":2,"score":0.7731783986091614},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.7349622249603271},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.6900732517242432},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6620671153068542},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6388656497001648},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5457985401153564},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5312813520431519},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5227770209312439},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.4521803855895996},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24800431728363037},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1463889479637146},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0795290470123291},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2013.6691568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1970779762","https://openalex.org/W2011078029","https://openalex.org/W2058858139","https://openalex.org/W2061601738","https://openalex.org/W2070162726","https://openalex.org/W2080234606","https://openalex.org/W2099601885","https://openalex.org/W2120755171","https://openalex.org/W2140509629","https://openalex.org/W2165769837","https://openalex.org/W2173213060","https://openalex.org/W6677710632"],"related_works":["https://openalex.org/W2943236215","https://openalex.org/W2394411596","https://openalex.org/W2737431648","https://openalex.org/W2349055795","https://openalex.org/W4226030716","https://openalex.org/W2599888081","https://openalex.org/W2971039361","https://openalex.org/W2725465928","https://openalex.org/W2358616404","https://openalex.org/W2352263435"],"abstract_inverted_index":{"Modern":[0],"parallel":[1,30],"computing":[2],"systems,":[3],"such":[4],"as":[5],"MapReduce,":[6,43],"often":[7,21,48],"assume":[8],"data":[9,19,61],"values":[10],"are":[11,47],"uniformly":[12],"distributed.":[13],"However,":[14],"in":[15,42,84,134,139],"the":[16,38,78,82,117,123,131,142],"real":[17,96],"world,":[18],"is":[20],"highly":[22],"skewed,":[23],"which":[24,76],"may":[25],"cause":[26],"workload":[27],"imbalance":[28,50],"among":[29],"running":[31],"tasks.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"study":[37],"reduce-phase":[39,118],"skew":[40],"problem":[41],"where":[44],"reduce":[45],"tasks":[46],"assgined":[49],"load":[51,86,111],"(in":[52],"terms":[53],"of":[54,104,130],"key":[55,66,79],"groups).":[56],"We":[57,89],"introduce":[58],"a":[59,85],"sketch-based":[60],"structure":[62],"for":[63],"capturing":[64],"MapReduce":[65],"group":[67],"size":[68],"statistics":[69],"and":[70,97,136],"present":[71],"an":[72,91],"optimal":[73],"packing":[74],"algorithm":[75,113],"assigns":[77],"groups":[80],"to":[81,141],"reducers":[83],"balancing":[87,112],"manner.":[88],"perform":[90],"empirical":[92],"evaluation":[93],"with":[94],"several":[95],"synthetic":[98],"datasets":[99],"over":[100],"two":[101],"distinct":[102],"types":[103],"applications.":[105],"The":[106],"results":[107],"show":[108],"that":[109],"our":[110],"can":[114,121],"strongly":[115],"mitigate":[116],"skew.":[119],"It":[120],"decrease":[122],"overall":[124],"job":[125],"completion":[126],"time":[127],"by":[128,137],"45.5%":[129],"default":[132],"settings":[133],"Hadoop":[135],"38.3%":[138],"comparison":[140],"state-of-the-art":[143],"solution.":[144]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
