{"id":"https://openalex.org/W2011078029","doi":"https://doi.org/10.14778/2350229.2350238","title":"Efficient multi-way theta-join processing using MapReduce","display_name":"Efficient multi-way theta-join processing using MapReduce","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W2011078029","doi":"https://doi.org/10.14778/2350229.2350238","mag":"2011078029"},"language":"en","primary_location":{"id":"doi:10.14778/2350229.2350238","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2350229.2350238","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5001241928","display_name":"Xiaofei Zhang","orcid":"https://orcid.org/0000-0003-2633-9929"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaofei Zhang","raw_affiliation_strings":["HKUST, Hong Kong","[HKUST, Hong Kong]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"[HKUST, Hong Kong]","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333516","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-8257-5806"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["HKUST, Hong Kong","[HKUST, Hong Kong]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"[HKUST, Hong Kong]","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100340868","display_name":"Min Wang","orcid":"https://orcid.org/0000-0001-7838-8947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Wang","raw_affiliation_strings":["HP Labs China, Beijing, China","HP Labs China Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs China, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"HP Labs China Beijing, China#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.7787,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":{"value":0.99022269,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"5","issue":"11","first_page":"1184","last_page":"1195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9990000128746033,"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":0.9987999796867371,"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/join","display_name":"Join (topology)","score":0.8636792302131653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.860299825668335},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4933454096317291},{"id":"https://openalex.org/keywords/sort-merge-join","display_name":"Sort-merge join","score":0.4730733335018158},{"id":"https://openalex.org/keywords/online-analytical-processing","display_name":"Online analytical processing","score":0.4622281491756439},{"id":"https://openalex.org/keywords/parallel-database","display_name":"Parallel database","score":0.4587327539920807},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.44220080971717834},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4101850986480713},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34612029790878296},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.25874391198158264},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.2362707555294037}],"concepts":[{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.8636792302131653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.860299825668335},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4933454096317291},{"id":"https://openalex.org/C203570394","wikidata":"https://www.wikidata.org/wiki/Q4060688","display_name":"Sort-merge join","level":3,"score":0.4730733335018158},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.4622281491756439},{"id":"https://openalex.org/C2777541480","wikidata":"https://www.wikidata.org/wiki/Q2051600","display_name":"Parallel database","level":2,"score":0.4587327539920807},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.44220080971717834},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4101850986480713},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34612029790878296},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.25874391198158264},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.2362707555294037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/2350229.2350238","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2350229.2350238","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.2426","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.2426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vldb.org/pvldb/vol5/p1184_xiaofeizhang_vldb2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.753.8281","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.753.8281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1208.0081.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-56962","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-56962","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4300000071525574},{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1507039213","https://openalex.org/W1509562192","https://openalex.org/W1574303240","https://openalex.org/W1665320540","https://openalex.org/W1985419898","https://openalex.org/W1993433750","https://openalex.org/W2010279913","https://openalex.org/W2035543557","https://openalex.org/W2037168816","https://openalex.org/W2048531653","https://openalex.org/W2060280513","https://openalex.org/W2061601738","https://openalex.org/W2100618668","https://openalex.org/W2103337291","https://openalex.org/W2107212030","https://openalex.org/W2116636977","https://openalex.org/W2126547925","https://openalex.org/W2127489049","https://openalex.org/W2129055634","https://openalex.org/W2143996311","https://openalex.org/W2145812340","https://openalex.org/W2151930506","https://openalex.org/W2161911872","https://openalex.org/W2169052472","https://openalex.org/W2172220707","https://openalex.org/W2173213060","https://openalex.org/W2586392344","https://openalex.org/W2912802084","https://openalex.org/W3104921985","https://openalex.org/W3145128584","https://openalex.org/W4299551239","https://openalex.org/W6634263952","https://openalex.org/W6758383543"],"related_works":["https://openalex.org/W2381211091","https://openalex.org/W2091359263","https://openalex.org/W1866159721","https://openalex.org/W4234452035","https://openalex.org/W2469706965","https://openalex.org/W1989231289","https://openalex.org/W2334867751","https://openalex.org/W3033055359","https://openalex.org/W4242221889","https://openalex.org/W1589496614"],"abstract_inverted_index":{"Multi-way":[0],"Theta-join":[1,27,66,97,125,183],"queries":[2,28,67,98],"are":[3],"powerful":[4],"in":[5,13,137,172,196],"describing":[6],"complex":[7],"relations":[8],"and":[9,22,133,165,198,204],"therefore":[10],"widely":[11,200],"employed":[12],"real":[14],"practices.":[15],"However,":[16],"existing":[17],"solutions":[18],"from":[19,70],"traditional":[20],"distributed":[21,37],"parallel":[23],"databases":[24],"for":[25,160],"multi-way":[26,65,96,124],"cannot":[29],"be":[30,44],"easily":[31],"extended":[32],"to":[33,43,46,89,127],"fit":[34],"a":[35,71,110,123,128,138,166,173,181],"shared-nothing":[36],"computing":[38],"paradigm,":[39],"which":[40],"is":[41,149],"proven":[42],"able":[45],"support":[47,90],"OLAP":[48],"applications":[49],"over":[50],"immense":[51],"data":[52],"volumes.":[53],"In":[54],"this":[55],"work,":[56],"we":[57],"study":[58],"the":[59,81,144,177,191,199,214],"problem":[60],"of":[61,64,95,112,130,168,180,213],"efficient":[62,93,178],"processing":[63,94,113,146,216],"using":[68,80],"MapReduce":[69,131,163,169,187],"cost-effective":[72],"perspective.":[73],"Although":[74],"there":[75],"have":[76],"been":[77,101],"some":[78],"works":[79],"(":[82],"key,":[83],"value":[84],")":[85],"pair-based":[86],"programming":[87],"model":[88],"join":[91,215],"operations,":[92],"has":[99],"never":[100],"fully":[102],"explored.":[103],"The":[104],"substantial":[105],"challenge":[106],"lies":[107],"in,":[108],"given":[109],"number":[111,129,167],"units":[114],"(that":[115],"can":[116],"run":[117],"Map":[118],"or":[119],"Reduce":[120],"tasks),":[121],"mapping":[122],"query":[126,192],"jobs":[132,170],"having":[134],"them":[135],"executed":[136,171],"well":[139],"scheduled":[140],"sequence,":[141],"such":[142],"that":[143],"total":[145],"time":[147],"span":[148],"minimized.":[150],"Our":[151],"solution":[152],"mainly":[153],"includes":[154],"two":[155],"parts:":[156],"1)":[157],"cost":[158],"metrics":[159],"both":[161],"single":[162],"job":[164],"certain":[174],"order;":[175],"2)":[176],"execution":[179],"chain-typed":[182],"with":[184,190],"only":[185],"one":[186],"job.":[188],"Comparing":[189],"evaluation":[193],"strategy":[194],"proposed":[195],"[23]":[197],"adopted":[201],"Pig":[202],"Latin":[203],"Hive":[205],"SQL":[206],"solutions,":[207],"our":[208],"method":[209],"achieves":[210],"significant":[211],"improvement":[212],"efficiency.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}