{"id":"https://openalex.org/W2156760512","doi":"https://doi.org/10.14778/1687627.1687677","title":"Composable, scalable, and accurate weight summarization of unaggregated data sets","display_name":"Composable, scalable, and accurate weight summarization of unaggregated data sets","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2156760512","doi":"https://doi.org/10.14778/1687627.1687677","mag":"2156760512"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687677","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687677","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5026385549","display_name":"Edith Cohen","orcid":"https://orcid.org/0000-0002-3926-8237"},"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":true,"raw_author_name":"Edith Cohen","raw_affiliation_strings":["AT&T Labs--Research, Florham Park, NJ"],"affiliations":[{"raw_affiliation_string":"AT&T Labs--Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048558842","display_name":"Nick Duffield","orcid":"https://orcid.org/0000-0001-7211-1584"},"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":"Nick Duffield","raw_affiliation_strings":["AT&T Labs--Research, Florham Park, NJ"],"affiliations":[{"raw_affiliation_string":"AT&T Labs--Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006699796","display_name":"Haim Kaplan","orcid":"https://orcid.org/0000-0001-9586-8002"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Haim Kaplan","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022565251","display_name":"Carsten Lund","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":"Carsten Lund","raw_affiliation_strings":["AT&T Labs--Research, Florham Park, NJ"],"affiliations":[{"raw_affiliation_string":"AT&T Labs--Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039232562","display_name":"Mikkel Thorup","orcid":"https://orcid.org/0000-0001-5237-1709"},"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":"Mikkel Thorup","raw_affiliation_strings":["AT&T Labs--Research, Florham Park, NJ"],"affiliations":[{"raw_affiliation_string":"AT&T Labs--Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026385549"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":1.0713,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78189655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2","issue":"1","first_page":"431","last_page":"442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9990000128746033,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9980999827384949,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8671284317970276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7832626104354858},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.6893282532691956},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.638253927230835},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.563154399394989},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5567803978919983},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5413626432418823},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5401273369789124},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.49345317482948303},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4379444122314453},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4336802363395691},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.327287495136261},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2370520830154419},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1849099099636078},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.18382886052131653}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8671284317970276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832626104354858},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.6893282532691956},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.638253927230835},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.563154399394989},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5567803978919983},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5413626432418823},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5401273369789124},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.49345317482948303},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4379444122314453},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4336802363395691},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.327287495136261},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2370520830154419},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1849099099636078},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.18382886052131653},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/1687627.1687677","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687677","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.4727","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.4727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/2/vldb09-85.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W579397108","https://openalex.org/W1519331563","https://openalex.org/W1571664355","https://openalex.org/W1588537298","https://openalex.org/W1964857063","https://openalex.org/W1972076792","https://openalex.org/W1977141583","https://openalex.org/W1979819093","https://openalex.org/W1993482412","https://openalex.org/W1998071119","https://openalex.org/W2001947543","https://openalex.org/W2013809345","https://openalex.org/W2030590905","https://openalex.org/W2031006315","https://openalex.org/W2044116626","https://openalex.org/W2045555847","https://openalex.org/W2049127440","https://openalex.org/W2068936568","https://openalex.org/W2074910460","https://openalex.org/W2085845250","https://openalex.org/W2111806841","https://openalex.org/W2113046370","https://openalex.org/W2119885577","https://openalex.org/W2152092514","https://openalex.org/W2152617961","https://openalex.org/W2341535507","https://openalex.org/W2752853835","https://openalex.org/W2800198128","https://openalex.org/W4206137901","https://openalex.org/W4232440580","https://openalex.org/W4233471163","https://openalex.org/W4237172715","https://openalex.org/W6635223630","https://openalex.org/W6669417358"],"related_works":["https://openalex.org/W4206710999","https://openalex.org/W2585167211","https://openalex.org/W1504893524","https://openalex.org/W1558947798","https://openalex.org/W2183743873","https://openalex.org/W2074496324","https://openalex.org/W2581171199","https://openalex.org/W2312215770","https://openalex.org/W2947885647","https://openalex.org/W4205473431"],"abstract_inverted_index":{"Many":[0],"data":[1,6,11,37,52,89,125,196,205,228],"sets":[2,7,206],"occur":[3],"as":[4,135],"unaggregated":[5,124],",":[8],"where":[9,126],"multiple":[10,97],"points":[12,38,90],"are":[13,44,91],"associated":[14,39],"with":[15,40],"each":[16],"key.":[17,42],"In":[18],"the":[19,23,25,31,34,41,85,108,150,177,181,187,222],"aggregate":[20,86],"view":[21],"of":[22,27,33,36,46,84,110,149,152,154,227],"data,":[24],"weight":[26,151],"a":[28,120,129,193],"key":[29],"is":[30,102,128,169,183],"sum":[32],"weights":[35],"Examples":[43],"measurements":[45],"IP":[47],"packet":[48],"header":[49],"streams,":[50],"distributed":[51],"streams":[53],"produced":[54],"by":[55,58],"events":[56],"registered":[57],"sensor":[59],"networks,":[60],"and":[61,76,81,99,131,134,203,224],"Web":[62],"page":[63],"or":[64,95,116],"multimedia":[65],"requests":[66],"to":[67,73,78,104,140,186,192],"context":[68],"distribution":[69],"servers.":[70],"We":[71,118],"aim":[72],"combine":[74],"sampling":[75],"aggregation":[77,101],"provide":[79],"accurate":[80],"efficient":[82],"summaries":[83,111,145],"view.":[87],"However,":[88],"scattered":[92],"in":[93],"time":[94],"across":[96],"servers":[98],"hence":[100],"subject":[103],"resource":[105,142],"constraints":[106],"on":[107],"size":[109],"that":[112,164,180,208],"can":[113,137],"be":[114,138],"stored":[115],"transmitted.":[117],"develop":[119],"summarization":[121,127,210],"framework":[122,211],"for":[123,216,221],"scalable":[130],"composable":[132],"operator,":[133],"such,":[136],"tailored":[139],"meet":[141],"constraints.":[143],"Our":[144],"support":[146],"unbiased":[147],"estimates":[148],"subpopulations":[153],"keys":[155],"specified":[156],"using":[157,201],"arbitrary":[158],"selection":[159],"predicates.":[160],"While":[161],"we":[162],"prove":[163],"under":[165],"such":[166],"scenarios":[167],"there":[168],"no":[170],"variance":[171,182],"optimal":[172],"scheme,":[173],"our":[174,209],"estimators":[175],"have":[176],"desirable":[178],"properties":[179],"progressively":[184],"closer":[185],"minimum":[188],"possible":[189],"when":[190],"applied":[191],"\"more\"":[194],"aggregated":[195],"set.":[197],"An":[198],"extensive":[199],"evaluation":[200],"synthetic":[202],"real":[204],"shows":[207],"outperforms":[212],"all":[213],"existing":[214],"schemes":[215],"this":[217],"fundamental":[218],"problem,":[219],"even":[220],"special":[223],"well-studied":[225],"case":[226],"streams.":[229]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}