{"id":"https://openalex.org/W1992363839","doi":"https://doi.org/10.1145/1247480.1247504","title":"On synopses for distinct-value estimation under multiset operations","display_name":"On synopses for distinct-value estimation under multiset operations","publication_year":2007,"publication_date":"2007-06-11","ids":{"openalex":"https://openalex.org/W1992363839","doi":"https://doi.org/10.1145/1247480.1247504","mag":"1992363839"},"language":"en","primary_location":{"id":"doi:10.1145/1247480.1247504","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1247480.1247504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 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/A5104043964","display_name":"Kevin Beyer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kevin Beyer","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090729930","display_name":"Peter J. Haas","orcid":"https://orcid.org/0000-0001-5694-3065"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter J. Haas","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036119025","display_name":"Berthold Reinwald","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Berthold Reinwald","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048704801","display_name":"Yannis Sismanis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Sismanis","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041227178","display_name":"Rainer Gemulla","orcid":"https://orcid.org/0000-0003-2762-0050"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Gemulla","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104043964"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":12.4541,"has_fulltext":false,"cited_by_count":183,"citation_normalized_percentile":{"value":0.98767246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9983000159263611,"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":0.9983000159263611,"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":0.998199999332428,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9975000023841858,"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/estimator","display_name":"Estimator","score":0.810722827911377},{"id":"https://openalex.org/keywords/multiset","display_name":"Multiset","score":0.7753064036369324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7639282941818237},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.7390317320823669},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5310421586036682},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47681161761283875},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3969399333000183},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37539875507354736},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2010975182056427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17241433262825012},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1552864909172058},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.08348873257637024}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.810722827911377},{"id":"https://openalex.org/C2779623528","wikidata":"https://www.wikidata.org/wiki/Q864377","display_name":"Multiset","level":2,"score":0.7753064036369324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639282941818237},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.7390317320823669},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5310421586036682},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47681161761283875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3969399333000183},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37539875507354736},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2010975182056427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17241433262825012},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1552864909172058},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08348873257637024},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1247480.1247504","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1247480.1247504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.230.7008","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.230.7008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mpi-sb.mpg.de/%7Ergemulla/publications/beyer07distinct.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":32,"referenced_works":["https://openalex.org/W1522055873","https://openalex.org/W1525949272","https://openalex.org/W1591710988","https://openalex.org/W1600795850","https://openalex.org/W1785933978","https://openalex.org/W1965996575","https://openalex.org/W1972074692","https://openalex.org/W1984566373","https://openalex.org/W1995437102","https://openalex.org/W2005731313","https://openalex.org/W2008365755","https://openalex.org/W2025051251","https://openalex.org/W2033803521","https://openalex.org/W2034302520","https://openalex.org/W2047061289","https://openalex.org/W2058991275","https://openalex.org/W2078361703","https://openalex.org/W2080745194","https://openalex.org/W2084757499","https://openalex.org/W2095595785","https://openalex.org/W2099480861","https://openalex.org/W2105733714","https://openalex.org/W2112400233","https://openalex.org/W2119885577","https://openalex.org/W2120074607","https://openalex.org/W2134786002","https://openalex.org/W2151310484","https://openalex.org/W2153329411","https://openalex.org/W2295428206","https://openalex.org/W2504767107","https://openalex.org/W2797333853","https://openalex.org/W6635082658"],"related_works":["https://openalex.org/W4300455649","https://openalex.org/W2296588302","https://openalex.org/W4328119206","https://openalex.org/W2033245919","https://openalex.org/W4252409532","https://openalex.org/W2006067547","https://openalex.org/W9228044","https://openalex.org/W3143753676","https://openalex.org/W2954483618","https://openalex.org/W3025714394"],"abstract_inverted_index":{"The":[0],"task":[1],"of":[2,6,19,72,84,130,138,146],"estimating":[3],"the":[4,70,87,144,188],"number":[5,71,83],"distinct":[7],"values":[8],"(DVs)":[9],"in":[10,15,21,74,86,100,110,179],"a":[11,16,37,54,82,168],"large":[12],"dataset":[13],"arises":[14],"wide":[17],"variety":[18],"settings":[20],"computer":[22],"science":[23],"and":[24,39,53,80,94,112,121,157,162,191,197,204],"elsewhere.":[25],"We":[26,142],"provide":[27],"DV":[28,96,122,153,207],"estimation":[29],"techniques":[30],"that":[31,151,194],"are":[32,155],"designed":[33],"for":[34,58,124],"use":[35,99,143],"within":[36],"flexible":[38],"scalable":[40],"\"synopsis":[41],"warehouse\"":[42],"architecture.":[43],"In":[44],"this":[45],"setting,":[46],"incoming":[47],"data":[48],"is":[49,56],"split":[50],"into":[51],"partitions":[52],"synopsis":[55,62,183],"created":[57,109],"each":[59,61],"partition;":[60],"can":[63,107,113,134,173],"then":[64,114],"be":[65,108,115],"used":[66],"to":[67,98,118,149,158,177,181,200],"quickly":[68],"estimate":[69],"DVs":[73],"its":[75],"corresponding":[76],"partition.":[77],"By":[78],"combining":[79],"extending":[81],"results":[85,175],"literature,":[88],"we":[89,172],"obtain":[90],"both":[91],"appropriate":[92],"synopses":[93,106,120,133,196],"novel":[95,169],"estimators":[97,154,198],"conjunction":[101],"with":[102],"these":[103],"synopses.":[104],"Our":[105,132],"parallel,":[111],"easily":[116],"combined":[117],"yield":[119],"estimates":[123,208],"arbitrary":[125],"unions,":[126],"intersections":[127],"or":[128],"differences":[129],"partitions.":[131],"also":[135],"handle":[136],"deletions":[137],"individual":[139],"partition":[140],"elements.":[141],"theory":[145,192],"order":[147,180],"statistics":[148],"show":[150],"our":[152,195],"unbiased,":[156],"establish":[159],"moment":[160],"formulas":[161],"sharp":[163],"error":[164],"bounds.":[165],"Based":[166],"on":[167],"limit":[170],"theorem,":[171],"exploit":[174],"due":[176],"Cohen":[178],"select":[182],"sizes":[184],"when":[185],"initially":[186],"designing":[187],"warehouse.":[189],"Experiments":[190],"indicate":[193],"lead":[199],"lower":[201],"computational":[202],"costs":[203],"more":[205],"accurate":[206],"than":[209],"previous":[210],"approaches.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}