{"id":"https://openalex.org/W2065280033","doi":"https://doi.org/10.1145/2516588.2516589","title":"Processing online aggregation on skewed data in mapreduce","display_name":"Processing online aggregation on skewed data in mapreduce","publication_year":2013,"publication_date":"2013-10-28","ids":{"openalex":"https://openalex.org/W2065280033","doi":"https://doi.org/10.1145/2516588.2516589","mag":"2065280033"},"language":"en","primary_location":{"id":"doi:10.1145/2516588.2516589","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2516588.2516589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth international workshop on Cloud data management","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/A5052084247","display_name":"Yantao Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yantao Gan","raw_affiliation_strings":["Renmin University of China, Beijing, China","Renmin Univ. of China, Beijing - China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Renmin Univ. of China, Beijing - China#TAB#","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101010043","display_name":"Xiaofeng Meng","orcid":"https://orcid.org/0000-0002-7889-2120"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Meng","raw_affiliation_strings":["Renmin University of China, Beijing, China","Renmin Univ. of China, Beijing - China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Renmin Univ. of China, Beijing - China#TAB#","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100308114","display_name":"Yingjie Shi","orcid":"https://orcid.org/0009-0006-7823-9515"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjie Shi","raw_affiliation_strings":["Renmin University of China, Beijing, China","Renmin Univ. of China, Beijing - China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Renmin Univ. of China, Beijing - China#TAB#","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":null,"first_page":"3","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994000196456909,"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/T11106","display_name":"Data Management and Algorithms","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9972000122070312,"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":0.8622972965240479},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.8081015348434448},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.7215125560760498},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.5608728528022766},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5303840041160583},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46048176288604736},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.4603689908981323},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4583415985107422},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.42521196603775024},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42372581362724304},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35745054483413696},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.13824942708015442},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.13346844911575317},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.13037005066871643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8622972965240479},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.8081015348434448},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.7215125560760498},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.5608728528022766},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5303840041160583},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46048176288604736},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.4603689908981323},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4583415985107422},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.42521196603775024},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42372581362724304},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35745054483413696},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.13824942708015442},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.13346844911575317},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.13037005066871643},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2516588.2516589","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2516588.2516589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth international workshop on Cloud data management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1513100972","https://openalex.org/W1595687138","https://openalex.org/W1597587459","https://openalex.org/W1976597724","https://openalex.org/W1991969632","https://openalex.org/W2020147322","https://openalex.org/W2035801804","https://openalex.org/W2044374606","https://openalex.org/W2119072946","https://openalex.org/W2120113238","https://openalex.org/W2122465391","https://openalex.org/W2132808937","https://openalex.org/W2136014429","https://openalex.org/W2164507334","https://openalex.org/W2167811976","https://openalex.org/W2296677182","https://openalex.org/W2397246664","https://openalex.org/W4229903866","https://openalex.org/W6630749417","https://openalex.org/W6635922872","https://openalex.org/W6684060480","https://openalex.org/W6712468459"],"related_works":["https://openalex.org/W3034924094","https://openalex.org/W3094954546","https://openalex.org/W1488708774","https://openalex.org/W1982811510","https://openalex.org/W4391100477","https://openalex.org/W2402189625","https://openalex.org/W4327779705","https://openalex.org/W4310560702","https://openalex.org/W2114396690","https://openalex.org/W4386778907"],"abstract_inverted_index":{"In":[0,121],"online":[1,40],"aggregation,":[2],"a":[3,43,77,114,141,158,164,169],"system":[4],"constantly":[5],"maintains":[6],"an":[7,14,49],"estimate":[8],"of":[9,31,79,86,91,99,175],"the":[10,25,29,68,84,89,97,130,133,188],"final":[11],"answer":[12],"to":[13,66,103,118,167],"aggregate":[15],"query":[16,34],"throughout":[17],"execution,":[18],"along":[19],"with":[20,190],"statistically":[21,191],"meaningful":[22],"bounds":[23],"for":[24,146],"estimate's":[26],"accuracy.":[27],"Given":[28],"popularity":[30],"ad-hoc":[32],"analytic":[33],"processing":[35],"over":[36,154],"enormous":[37],"datasets,":[38],"providing":[39],"aggregation":[41],"in":[42,132,157,187],"large-scale,":[44],"MapReduce":[45,69],"environment":[46,61],"is":[47,94],"therefore":[48],"emerging":[50],"important":[51],"application":[52],"need.":[53],"However,":[54],"existing":[55],"work":[56],"targeted":[57],"at":[58,106],"single-node":[59],"centralized":[60],"cannot":[62,110],"be":[63,111],"easily":[64],"extended":[65],"fit":[67],"paradigm.":[70],"The":[71],"substantial":[72],"challenge":[73],"lies":[74],"in,":[75],"given":[76,83],"number":[78],"input":[80],"blocks,":[81],"and":[82],"prevalence":[85],"data":[87,127],"skew,":[88],"runtime":[90],"upstream":[92],"operators":[93,105],"uneven,":[95],"so":[96],"set":[98,174],"intermediate":[100],"results":[101],"delivered":[102],"downstream":[104],"any":[107],"particular":[108],"point":[109],"seen":[112],"as":[113],"random":[115],"sample,":[116],"leading":[117],"biased":[119],"estimates.":[120],"this":[122],"paper,":[123],"we":[124,139,162],"analyze":[125],"how":[126],"skew":[128,198],"breaks":[129],"randomness":[131],"distributed":[134,159],"environment.":[135,160],"To":[136],"address":[137],"that,":[138],"present":[140],"keep-order":[142],"approach":[143],"that":[144,148,178],"accounts":[145],"biases":[147],"can":[149,181],"arise":[150],"when":[151,196],"estimating":[152],"aggregates":[153],"skewed":[155],"dataset":[156],"Moreover,":[161],"provide":[163,182],"pre-computing":[165],"method":[166,180],"promise":[168],"fast":[170],"result":[171],"rate.":[172],"A":[173],"experiments":[176],"indicates":[177],"our":[179],"reasonable":[183],"precise":[184],"estimates":[185],"early":[186],"execution":[189],"valid":[192],"confidence":[193],"bounds,":[194],"even":[195],"significant":[197],"exists.":[199]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}