{"id":"https://openalex.org/W2061601738","doi":"https://doi.org/10.1145/1989323.1989423","title":"Processing theta-joins using MapReduce","display_name":"Processing theta-joins using MapReduce","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2061601738","doi":"https://doi.org/10.1145/1989323.1989423","mag":"2061601738"},"language":"en","primary_location":{"id":"doi:10.1145/1989323.1989423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of 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/A5009076607","display_name":"Alper Okcan","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alper Okcan","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049802784","display_name":"Mirek Riedewald","orcid":"https://orcid.org/0000-0002-6102-7472"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mirek Riedewald","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009076607"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":79.3155,"has_fulltext":false,"cited_by_count":238,"citation_normalized_percentile":{"value":0.99926088,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"949","last_page":"960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991000294685364,"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":0.9991000294685364,"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":0.998199999332428,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9954000115394592,"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/joins","display_name":"Joins","score":0.9771112203598022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8474084138870239},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.8003753423690796},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.7136006355285645},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46611645817756653},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.46190932393074036},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.411357045173645},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.29587823152542114},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1917228400707245},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09316346049308777}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9771112203598022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8474084138870239},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.8003753423690796},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.7136006355285645},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46611645817756653},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46190932393074036},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.411357045173645},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29587823152542114},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1917228400707245},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09316346049308777},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":1,"locations":[{"id":"doi:10.1145/1989323.1989423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1500547548","https://openalex.org/W1582870960","https://openalex.org/W1597532222","https://openalex.org/W1997020216","https://openalex.org/W2043099794","https://openalex.org/W2075620950","https://openalex.org/W2098935637","https://openalex.org/W2100830825","https://openalex.org/W2114303224","https://openalex.org/W2119714163","https://openalex.org/W2141267666","https://openalex.org/W2143108641","https://openalex.org/W2151930506","https://openalex.org/W2154894831","https://openalex.org/W2158237121","https://openalex.org/W2173213060","https://openalex.org/W2261815431","https://openalex.org/W6629856530","https://openalex.org/W6635650928"],"related_works":["https://openalex.org/W2488852078","https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W1496672428","https://openalex.org/W650102067","https://openalex.org/W2172084996","https://openalex.org/W2397450670"],"abstract_inverted_index":{"Joins":[0],"are":[1,9],"essential":[2],"for":[3,89,112],"many":[4],"data":[5,58],"analysis":[6],"tasks,":[7],"but":[8],"not":[10,33,137,162],"supported":[11],"directly":[12],"by":[13,148],"the":[14,38,125,132,138,167,172],"MapReduce":[15,29,97,168],"paradigm.":[16],"While":[17],"there":[18],"has":[19],"been":[20],"progress":[21],"on":[22,61],"equi-joins,":[23],"implementation":[24],"of":[25,40,70,115,131,174],"join":[26,45,66,116],"algorithms":[27,154],"in":[28,30,75,94],"general":[31],"is":[32,119,136],"sufficiently":[34],"understood.":[35],"We":[36],"study":[37],"problem":[39],"how":[41,143],"to":[42,47,122,144,166],"map":[43],"arbitrary":[44,91],"conditions":[46],"Map":[48],"and":[49,71,107,159],"Reduce":[50],"functions,":[51],"i.e.,":[52],"a":[53,82,95,113],"parallel":[54],"infrastructure":[55],"that":[56,111],"controls":[57],"flow":[59],"based":[60],"key-equality":[62],"only.":[63],"Our":[64],"proposed":[65],"model":[67],"simplifies":[68],"creation":[69],"reasoning":[72],"about":[73],"joins":[74,92],"MapReduce.":[76],"Using":[77],"this":[78],"model,":[79],"we":[80,108,141],"derive":[81],"surprisingly":[83],"simple":[84],"randomized":[85],"algorithm,":[86],"called":[87],"1-Bucket-Theta,":[88],"implementing":[90],"(theta-joins)":[93],"single":[96],"job.":[98],"This":[99],"algorithm":[100],"only":[101],"requires":[102],"minimal":[103],"statistics":[104],"(input":[105],"cardinality)":[106],"provide":[109],"evidence":[110],"variety":[114],"problems,":[117],"it":[118],"either":[120],"close":[121],"optimal":[123],"or":[124],"best":[126,139],"possible":[127],"option.":[128],"For":[129],"some":[130],"problems":[133],"where":[134],"1-Bucket-Theta":[135],"choice,":[140],"show":[142,171],"achieve":[145],"better":[146],"performance":[147],"exploiting":[149],"additional":[150],"input":[151],"statistics.":[152],"All":[153],"can":[155],"be":[156],"made":[157],"'memory-aware',":[158],"they":[160],"do":[161],"require":[163],"any":[164],"modifications":[165],"environment.":[169],"Experiments":[170],"effectiveness":[173],"our":[175],"approach.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":36},{"year":2015,"cited_by_count":28},{"year":2014,"cited_by_count":39},{"year":2013,"cited_by_count":34},{"year":2012,"cited_by_count":25}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}