{"id":"https://openalex.org/W2150569458","doi":"https://doi.org/10.1145/1007568.1007575","title":"Holistic UDAFs at streaming speeds","display_name":"Holistic UDAFs at streaming speeds","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2150569458","doi":"https://doi.org/10.1145/1007568.1007575","mag":"2150569458"},"language":"en","primary_location":{"id":"doi:10.1145/1007568.1007575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 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/A5031896681","display_name":"Graham Cormode","orcid":"https://orcid.org/0000-0002-0698-0922"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Graham Cormode","raw_affiliation_strings":["Rutgers University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103350641","display_name":"Theodore Johnson","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theodore Johnson","raw_affiliation_strings":["AT&amp;T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110197814","display_name":"Flip Korn","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Flip Korn","raw_affiliation_strings":["AT&amp;T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075159410","display_name":"S. Muthukrishnan","orcid":"https://orcid.org/0009-0007-8936-5709"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"S. Muthukrishnan","raw_affiliation_strings":["Rutgers University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049422372","display_name":"Oliver Spatscheck","orcid":"https://orcid.org/0000-0003-1555-6303"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oliver Spatscheck","raw_affiliation_strings":["AT&amp;T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&amp;T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031896681"],"corresponding_institution_ids":["https://openalex.org/I4210096112"],"apc_list":null,"apc_paid":null,"fwci":7.7153,"has_fulltext":false,"cited_by_count":126,"citation_normalized_percentile":{"value":0.97940623,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994000196456909,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9986000061035156,"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":0.8740385174751282},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.7428550124168396},{"id":"https://openalex.org/keywords/quantile","display_name":"Quantile","score":0.6108593344688416},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.60462486743927},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5695288181304932},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5244917273521423},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.5022637844085693},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49828362464904785},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.49061813950538635},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.48929545283317566},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.45508697628974915},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3833693861961365},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.28771349787712097},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1720145046710968},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.08138471841812134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8740385174751282},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.7428550124168396},{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.6108593344688416},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.60462486743927},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5695288181304932},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5244917273521423},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.5022637844085693},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49828362464904785},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.49061813950538635},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.48929545283317566},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.45508697628974915},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3833693861961365},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28771349787712097},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1720145046710968},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.08138471841812134},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1007568.1007575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.113.2257","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.113.2257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dimacs.rutgers.edu/~graham/pubs/papers/cjkmss-streamudaf.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.2012","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.2012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://public.research.att.com/~divesh/papers/cjkmss2004-udaf.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.94.8357","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.94.8357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rutgers.edu/~muthu/udafs.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W89074110","https://openalex.org/W176053229","https://openalex.org/W1481218190","https://openalex.org/W1493892051","https://openalex.org/W1542652451","https://openalex.org/W1564015926","https://openalex.org/W1607538671","https://openalex.org/W1766932551","https://openalex.org/W1965972569","https://openalex.org/W1992023276","https://openalex.org/W1998783890","https://openalex.org/W2001474264","https://openalex.org/W2013092187","https://openalex.org/W2025051251","https://openalex.org/W2028660080","https://openalex.org/W2028859573","https://openalex.org/W2053075747","https://openalex.org/W2064379477","https://openalex.org/W2068714596","https://openalex.org/W2069980026","https://openalex.org/W2080234606","https://openalex.org/W2081189989","https://openalex.org/W2100369465","https://openalex.org/W2103201239","https://openalex.org/W2106163100","https://openalex.org/W2107832410","https://openalex.org/W2112452856","https://openalex.org/W2113139394","https://openalex.org/W2118828104","https://openalex.org/W2128869116","https://openalex.org/W2134786002","https://openalex.org/W2144261930","https://openalex.org/W2148706674","https://openalex.org/W2161463763","https://openalex.org/W2161569281","https://openalex.org/W2169593628","https://openalex.org/W2398660820","https://openalex.org/W3004286518","https://openalex.org/W6603630036","https://openalex.org/W6712268384"],"related_works":["https://openalex.org/W4246591448","https://openalex.org/W2801575137","https://openalex.org/W2167004500","https://openalex.org/W2023497185","https://openalex.org/W2151831402","https://openalex.org/W4224062203","https://openalex.org/W4310912227","https://openalex.org/W2102476072","https://openalex.org/W2122290246","https://openalex.org/W2156668715"],"abstract_inverted_index":{"Many":[0],"algorithms":[1,33,65],"have":[2],"been":[3,22],"proposed":[4],"to":[5,24,30,41,60,89],"approximate":[6],"holistic":[7,67,92],"aggregates,":[8],"such":[9],"as":[10],"quantiles":[11,117],"and":[12,40,63,83,85,95,109,118],"heavy":[13,119],"hitters,":[14],"over":[15],"data":[16,36,71,101],"streams.":[17],"However,":[18],"little":[19],"work":[20],"has":[21],"done":[23],"explore":[25],"what":[26],"techniques":[27,88],"are":[28],"required":[29],"incorporate":[31,61],"these":[32,91],"in":[34,45,99],"a":[35,70],"stream":[37,72,102],"query":[38,75],"processor,":[39],"make":[42,90],"them":[43],"useful":[44],"practice.In":[46],"this":[47],"paper,":[48],"we":[49],"study":[50],"the":[51],"performance":[52,81,106],"implications":[53],"of":[54,123],"using":[55,107],"user-defined":[56],"aggregate":[57],"functions":[58],"(UDAFs)":[59],"selection-based":[62],"sketch-based":[64],"for":[66,97],"aggregates":[68],"into":[69],"management":[73],"system's":[74],"processing":[76],"architecture.":[77],"We":[78,104],"identify":[79],"key":[80],"bottlenecks":[82],"tradeoffs,":[84],"propose":[86],"novel":[87],"UDAFs":[93],"fast":[94],"space-efficient":[96],"use":[98],"high-speed":[100],"applications.":[103],"evaluate":[105],"generated":[108],"actual":[110],"IP":[111],"packet":[112],"data,":[113],"focusing":[114],"on":[115],"approximating":[116],"hitters.":[120],"The":[121],"best":[122],"our":[124],"current":[125],"implementations":[126],"can":[127],"process":[128],"streaming":[129],"queries":[130],"at":[131],"OC48":[132],"speeds":[133],"(2x":[134],"2.4Gbps).":[135]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}
