{"id":"https://openalex.org/W2118924829","doi":"https://doi.org/10.1145/872757.872765","title":"Approximate join processing over data streams","display_name":"Approximate join processing over data streams","publication_year":2003,"publication_date":"2003-06-09","ids":{"openalex":"https://openalex.org/W2118924829","doi":"https://doi.org/10.1145/872757.872765","mag":"2118924829"},"language":"en","primary_location":{"id":"doi:10.1145/872757.872765","doi":"https://doi.org/10.1145/872757.872765","is_oa":false,"landing_page_url":"https://doi.org/10.1145/872757.872765","pdf_url":null,"source":{"id":"https://openalex.org/S4393915683","display_name":"ACM SIGMOD International Conference on Management of Data (SIGMOD)","issn_l":"0730-8078","issn":["0730-8078"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2003 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5102425985","display_name":"Abhinandan Das","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinandan Das","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023537206","display_name":"Johannes E. Gehrke","orcid":"https://orcid.org/0009-0006-6293-5209","observed_orcids":["https://orcid.org/0009-0006-6293-5209"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johannes Gehrke","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049802784","display_name":"Mirek Riedewald","orcid":"https://orcid.org/0000-0002-6102-7472","observed_orcids":["https://orcid.org/0000-0002-6102-7472"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mirek Riedewald","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":17.2206,"has_fulltext":false,"cited_by_count":276,"citation_normalized_percentile":{"value":0.99445061,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":92,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"51"},"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/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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":9.999999747378752e-05,"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/T12761","display_name":"Data Stream Mining Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/stream-processing","display_name":"stream processing","score":0.7319999933242798},{"id":"https://openalex.org/keywords/approximate-query-processing","display_name":"approximate query processing","score":0.7360000014305115},{"id":"https://openalex.org/keywords/resource-constrained-systems","display_name":"resource-constrained systems","score":0.6290000081062317},{"id":"https://openalex.org/keywords/online-algorithms","display_name":"online algorithms","score":0.6909999847412109},{"id":"https://openalex.org/keywords/offline-algorithms","display_name":"offline algorithms","score":0.9120000004768372}],"concepts":[{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.9441386461257935},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8700436353683472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568894863128662},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.8192151188850403},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6147845387458801},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.5871443748474121},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5438580513000488},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4813823997974396},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4623355567455292},{"id":"https://openalex.org/C188805328","wikidata":"https://www.wikidata.org/wiki/Q4060691","display_name":"Hash join","level":3,"score":0.4554429352283478},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.44038254022598267},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.4228425621986389},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.4109190106391907},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3305380940437317},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.29664650559425354},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08909979462623596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08515763282775879},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/872757.872765","doi":"https://doi.org/10.1145/872757.872765","is_oa":false,"landing_page_url":"https://doi.org/10.1145/872757.872765","pdf_url":null,"source":{"id":"https://openalex.org/S4393915683","display_name":"ACM SIGMOD International Conference on Management of Data (SIGMOD)","issn_l":"0730-8078","issn":["0730-8078"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2003 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.12.7195","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.7195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/johannes/papers/2003/sigmod2003-loadShedding.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.3875","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.3875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.virginia.edu/~son/cs851/stream/papers/p40-das.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W162964049","https://openalex.org/W306123262","https://openalex.org/W1493149182","https://openalex.org/W1684311429","https://openalex.org/W1784244685","https://openalex.org/W1964857063","https://openalex.org/W2001474264","https://openalex.org/W2004110412","https://openalex.org/W2004154913","https://openalex.org/W2053075747","https://openalex.org/W2106163100","https://openalex.org/W2112452856","https://openalex.org/W2118828104","https://openalex.org/W2125101937","https://openalex.org/W2128869116","https://openalex.org/W2128967345","https://openalex.org/W2132461362","https://openalex.org/W2132520482","https://openalex.org/W2132837277","https://openalex.org/W2135499008","https://openalex.org/W2140894225","https://openalex.org/W2144771673","https://openalex.org/W2147232895","https://openalex.org/W2155370486","https://openalex.org/W2169593628","https://openalex.org/W2201552871","https://openalex.org/W2229915657","https://openalex.org/W2613161123","https://openalex.org/W2747485148","https://openalex.org/W4232534713","https://openalex.org/W4235359639","https://openalex.org/W4237172715","https://openalex.org/W4253103473"],"related_works":["https://openalex.org/W2122135452","https://openalex.org/W7097716093","https://openalex.org/W2036224420","https://openalex.org/W131297827","https://openalex.org/W7100526781","https://openalex.org/W1870651561","https://openalex.org/W2154787987","https://openalex.org/W2597027970","https://openalex.org/W1998164759","https://openalex.org/W1964417640"],"abstract_inverted_index":{"We":[0,42,69],"consider":[1,71],"the":[2,33,39,59,72,79,105,124,131,135],"problem":[3],"of":[4,35,61,64,74,107,126],"approximating":[5],"sliding":[6],"window":[7],"joins":[8],"over":[9],"data":[10,14,40,49,102],"streams":[11,136],"in":[12,32,133],"a":[13,65,94,119],"stream":[15,50],"processing":[16],"system":[17],"with":[18,26,98,112],"limited":[19],"resources.":[20],"In":[21,93],"our":[22,108],"model,":[23],"we":[24,54,83,103,117],"deal":[25],"resource":[27],"constraints":[28],"by":[29],"shedding":[30],"load":[31],"form":[34],"dropping":[36],"tuples":[37,77],"from":[38],"streams.":[41],"first":[43],"discuss":[44],"alternate":[45],"architectural":[46],"models":[47],"for":[48,58,91,114,139],"join":[51,132],"processing,":[52],"and":[53,82,87,100],"survey":[55],"suitable":[56],"measures":[57],"quality":[60,80],"an":[62],"approximation":[63],"set-valued":[66],"query":[67],"result.":[68],"then":[70],"number":[73],"generated":[75],"result":[76],"as":[78],"measure,":[81],"give":[84],"optimal":[85],"offline":[86],"fast":[88],"online":[89],"algorithms":[90],"it.":[92],"thorough":[95],"experimental":[96],"study":[97],"synthetic":[99],"real":[101],"show":[104],"efficacy":[106],"solutions.":[109],"For":[110],"applications":[111],"demand":[113],"exact":[115],"results":[116],"introduce":[118],"new":[120],"Archive-metric":[121],"which":[122],"captures":[123],"amount":[125],"work":[127],"needed":[128],"to":[129],"complete":[130],"case":[134],"are":[137],"archived":[138],"later":[140],"processing.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":14}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}