{"id":"https://openalex.org/W2164329923","doi":"https://doi.org/10.1145/2501928.2501932","title":"Toward intersection filter-based optimization for joins in MapReduce","display_name":"Toward intersection filter-based optimization for joins in MapReduce","publication_year":2013,"publication_date":"2013-08-13","ids":{"openalex":"https://openalex.org/W2164329923","doi":"https://doi.org/10.1145/2501928.2501932","mag":"2164329923"},"language":"en","primary_location":{"id":"doi:10.1145/2501928.2501932","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2501928.2501932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Cloud Intelligence","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/A5056921599","display_name":"Thuong\u2010Cang Phan","orcid":"https://orcid.org/0000-0002-4807-2463"},"institutions":[{"id":"https://openalex.org/I198244214","display_name":"Universit\u00e9 Clermont Auvergne","ror":"https://ror.org/01a8ajp46","country_code":"FR","type":"education","lineage":["https://openalex.org/I198244214"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Thuong-Cang Phan","raw_affiliation_strings":["Blaise Pascal University, Clermont-Ferrand, France"],"affiliations":[{"raw_affiliation_string":"Blaise Pascal University, Clermont-Ferrand, France","institution_ids":["https://openalex.org/I198244214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023360779","display_name":"Laurent d\u2019Orazio","orcid":"https://orcid.org/0000-0001-8614-1848"},"institutions":[{"id":"https://openalex.org/I198244214","display_name":"Universit\u00e9 Clermont Auvergne","ror":"https://ror.org/01a8ajp46","country_code":"FR","type":"education","lineage":["https://openalex.org/I198244214"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent d'Orazio","raw_affiliation_strings":["Blaise Pascal University, Clermont-Ferrand, France"],"affiliations":[{"raw_affiliation_string":"Blaise Pascal University, Clermont-Ferrand, France","institution_ids":["https://openalex.org/I198244214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108536045","display_name":"Philippe Rigaux","orcid":"https://orcid.org/0000-0002-9189-7292"},"institutions":[{"id":"https://openalex.org/I4210145724","display_name":"Centre d'Etudes et De Recherche en Informatique et Communications","ror":"https://ror.org/044j5mm75","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210145724"]},{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Philippe Rigaux","raw_affiliation_strings":["CEDRICm CNAM, Paris, France"],"affiliations":[{"raw_affiliation_string":"CEDRICm CNAM, Paris, France","institution_ids":["https://openalex.org/I4210145724","https://openalex.org/I124158823"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056921599"],"corresponding_institution_ids":["https://openalex.org/I198244214"],"apc_list":null,"apc_paid":null,"fwci":1.8123,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.87605582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9997000098228455,"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/T11478","display_name":"Caching and Content Delivery","score":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9933000206947327,"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/T11342","display_name":"Carbon and Quantum Dots Applications","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.9695926904678345},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.9097169637680054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8497633934020996},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.8100827932357788},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.7616458535194397},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.6401572823524475},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6377413868904114},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5299226641654968},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4452308416366577},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43032971024513245},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3691664934158325},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.355352520942688},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27225202322006226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14973998069763184},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08520585298538208}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9695926904678345},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.9097169637680054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8497633934020996},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.8100827932357788},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.7616458535194397},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.6401572823524475},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6377413868904114},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5299226641654968},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4452308416366577},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43032971024513245},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3691664934158325},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.355352520942688},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27225202322006226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14973998069763184},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08520585298538208},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2501928.2501932","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2501928.2501932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Cloud Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5600000023841858,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1544119352","https://openalex.org/W1558092379","https://openalex.org/W1852059679","https://openalex.org/W1916323520","https://openalex.org/W1970196737","https://openalex.org/W1993284846","https://openalex.org/W2001040824","https://openalex.org/W2012802704","https://openalex.org/W2033258621","https://openalex.org/W2037168816","https://openalex.org/W2043099794","https://openalex.org/W2044936152","https://openalex.org/W2075620950","https://openalex.org/W2097880677","https://openalex.org/W2104615308","https://openalex.org/W2123845384","https://openalex.org/W2125520775","https://openalex.org/W2126547925","https://openalex.org/W2146183750","https://openalex.org/W2151930506","https://openalex.org/W2154894831","https://openalex.org/W2156660460","https://openalex.org/W2166310193","https://openalex.org/W2169486917","https://openalex.org/W2491312619","https://openalex.org/W2495705296","https://openalex.org/W2912591062","https://openalex.org/W6632514215"],"related_works":["https://openalex.org/W2139429256","https://openalex.org/W2104615308","https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W650102067","https://openalex.org/W3086237447","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W1496672428","https://openalex.org/W2589740103"],"abstract_inverted_index":{"MapReduce":[0,36,98],"has":[1],"become":[2],"an":[3,64],"attractive":[4],"and":[5,49,116,119,139],"dominant":[6],"model":[7,14],"for":[8],"processing":[9,134],"large-scale":[10],"datasets.":[11,78],"However,":[12],"this":[13],"is":[15,145],"not":[16],"designed":[17],"to":[18,71,84,94,127,147],"directly":[19],"support":[20],"operations":[21],"with":[22],"multiple":[23],"inputs":[24],"as":[25],"joins.":[26],"Many":[27],"studies":[28],"on":[29,68],"join":[30,34,117,133],"algorithms":[31],"including":[32],"Bloom":[33,88],"in":[35,103],"have":[37,43],"been":[38],"conducted":[39],"but":[40],"they":[41],"still":[42],"too":[44],"much":[45],"non-joining":[46],"data":[47],"generated":[48],"transmitted":[50],"over":[51],"the":[52,60,86,92,128,143],"network.":[53],"This":[54],"research":[55,144],"will":[56,100],"help":[57],"us":[58],"eliminate":[59],"problem":[61],"by":[62],"providing":[63],"intersection":[65,87,131],"filter":[66,93],"based":[67],"probabilistic":[69],"models":[70],"remove":[72],"most":[73],"disjoint":[74],"elements":[75],"between":[76],"two":[77],"Namely,":[79],"three":[80],"ways":[81],"are":[82],"proposed":[83],"build":[85],"filter.":[89],"To":[90],"apply":[91],"joins,":[95],"a":[96,104,124,155],"corresponding":[97],"job":[99],"be":[101,148],"adjusted":[102],"consistent":[105],"way":[106],"without":[107],"increasing":[108],"related":[109],"costs.":[110,122,141],"We":[111],"then":[112],"consider":[113],"two-way":[114],"joins":[115,159],"cascades":[118],"analyze":[120],"their":[121],"As":[123],"result,":[125],"thanks":[126],"high":[129],"accuracy":[130],"filter,":[132],"can":[135],"minimize":[136],"disk":[137],"I/O":[138],"communication":[140],"Finally,":[142],"proved":[146],"more":[149],"effective":[150],"than":[151],"existing":[152],"solutions":[153],"through":[154],"cost-based":[156],"comparison":[157],"of":[158],"using":[160],"different":[161],"approaches.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
