{"id":"https://openalex.org/W2128613414","doi":"https://doi.org/10.1145/1353343.1353414","title":"A stratified approach to progressive approximate joins","display_name":"A stratified approach to progressive approximate joins","publication_year":2008,"publication_date":"2008-03-25","ids":{"openalex":"https://openalex.org/W2128613414","doi":"https://doi.org/10.1145/1353343.1353414","mag":"2128613414"},"language":"en","primary_location":{"id":"doi:10.1145/1353343.1353414","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1353343.1353414","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1353343.1353414","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th international conference on Extending database technology: Advances in database technology","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/1353343.1353414","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089418748","display_name":"Wee Hyong Tok","orcid":"https://orcid.org/0000-0001-8346-5003"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wee Hyong Tok","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025922937","display_name":"St\u00e9phane Bressan","orcid":"https://orcid.org/0000-0001-5536-3296"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"St\u00e9phane Bressan","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019988958","display_name":"Mong Li Lee","orcid":"https://orcid.org/0000-0002-9636-388X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mong-Li Lee","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.7644,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.67760934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8559812307357788},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8083010911941528},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5930470824241638},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.59202641248703},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5487266182899475},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5312162637710571},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5241320729255676},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49886107444763184},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4901962876319885},{"id":"https://openalex.org/keywords/representativeness-heuristic","display_name":"Representativeness heuristic","score":0.479636013507843},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37833303213119507},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2511363923549652},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08083873987197876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07873561978340149}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8559812307357788},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8083010911941528},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5930470824241638},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.59202641248703},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5487266182899475},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5312162637710571},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5241320729255676},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49886107444763184},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4901962876319885},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.479636013507843},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37833303213119507},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2511363923549652},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08083873987197876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07873561978340149},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1353343.1353414","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1353343.1353414","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1353343.1353414","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th international conference on Extending database technology: Advances in database technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.377.1685","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.377.1685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.edbt.org/Proceedings/2008-Nantes/papers/p582-Tok.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.380.8875","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.380.8875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu/~steph/papers/edbt2008.pdf","raw_type":"text"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/41436","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/41436","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/1353343.1353414","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1353343.1353414","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1353343.1353414","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th international conference on Extending database technology: Advances in database technology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2128613414.pdf","grobid_xml":"https://content.openalex.org/works/W2128613414.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1486039312","https://openalex.org/W1563683808","https://openalex.org/W1592355944","https://openalex.org/W1594122454","https://openalex.org/W1848127982","https://openalex.org/W1964857063","https://openalex.org/W2001474264","https://openalex.org/W2069980026","https://openalex.org/W2099665113","https://openalex.org/W2112452856","https://openalex.org/W2118828104","https://openalex.org/W2118924829","https://openalex.org/W2119885577","https://openalex.org/W2122135452","https://openalex.org/W2132510297","https://openalex.org/W2132520482","https://openalex.org/W2134786002","https://openalex.org/W2140598739","https://openalex.org/W2146950091","https://openalex.org/W2229915657","https://openalex.org/W2261815431","https://openalex.org/W3004286518","https://openalex.org/W4235359639","https://openalex.org/W6628939419","https://openalex.org/W6635371082"],"related_works":["https://openalex.org/W2378924333","https://openalex.org/W2362446711","https://openalex.org/W2623584706","https://openalex.org/W1495801388","https://openalex.org/W2551308855","https://openalex.org/W3022897553","https://openalex.org/W4287779284","https://openalex.org/W2001785422","https://openalex.org/W2605169415","https://openalex.org/W2082671441"],"abstract_inverted_index":{"Users":[0],"often":[1],"do":[2],"not":[3],"require":[4],"a":[5,14],"complete":[6],"answer":[7],"to":[8,20,50,56,82,89],"their":[9],"query":[10,39],"but":[11],"rather":[12],"only":[13],"sample.":[15,152],"They":[16],"expect":[17],"the":[18,23,27,33,38,75,98,105,122,140,151],"sample":[19],"be":[21,57],"either":[22],"largest":[24],"possible":[25],"or":[26],"most":[28],"representative":[29],"(or":[30],"both)":[31],"given":[32],"resources":[34],"available.":[35],"We":[36,109,119],"call":[37],"processing":[40,79,86],"techniques":[41],"that":[42],"deliver":[43],"such":[44,103],"results":[45,64],"'approximate'.":[46],"Processing":[47],"of":[48,52,80,97,102,124,144,148,150],"queries":[49,81],"streams":[51,84],"data":[53,66,83],"is":[54,87],"said":[55],"'progressive'":[58],"when":[59,85],"it":[60],"can":[61],"continuously":[62],"produce":[63],"as":[65],"arrives.":[67],"In":[68,92,136],"this":[69],"paper,":[70],"we":[71,94,138],"are":[72],"interested":[73],"in":[74],"progressive":[76,106,115],"and":[77,111,127,146],"approximate":[78,107,116],"limited":[88],"main":[90,99],"memory.":[91],"particular,":[93],"study":[95,139],"one":[96],"building":[100],"blocks":[101],"processing:":[104],"join.":[108],"devise":[110],"present":[112],"several":[113],"novel":[114],"join":[117],"algorithms.":[118],"empirically":[120],"evaluate":[121],"performance":[123],"our":[125],"algorithms":[126,131],"compare":[128],"them":[129],"with":[130],"based":[132],"on":[133],"existing":[134],"techniques.":[135],"particular":[137],"trade-off":[141],"between":[142],"maximization":[143,147],"throughput":[145],"representativeness":[149]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}