{"id":"https://openalex.org/W2001183701","doi":"https://doi.org/10.1145/1807085.1807099","title":"Optimal sampling from distributed streams","display_name":"Optimal sampling from distributed streams","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2001183701","doi":"https://doi.org/10.1145/1807085.1807099","mag":"2001183701"},"language":"en","primary_location":{"id":"doi:10.1145/1807085.1807099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807085.1807099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-ninth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","raw_type":"proceedings-article"},"type":"conference-paper","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/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":"Graham Cormode","raw_affiliation_strings":["AT&T Labs - Research, Florham Park, NJ, USA","AT&T Labs---Research, Florham Park, NJ, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs---Research, Florham Park, NJ, USA#TAB#","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/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Muthukrishnan","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA","Rutgers University , Piscataway, NJ , USA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Rutgers University , Piscataway, NJ , USA ,","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009196125","display_name":"Ke Yi","orcid":"https://orcid.org/0000-0002-2178-3716"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ke Yi","raw_affiliation_strings":["HKUST, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418224","display_name":"Qin Zhang","orcid":"https://orcid.org/0000-0002-6851-3115"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qin Zhang","raw_affiliation_strings":["HKUST, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.8411394953727722},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.7588688731193542},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.6432723999023438},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6149227619171143},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.596112847328186},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.5570594668388367},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.530903697013855},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5269219279289246},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5015003681182861},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4936150312423706},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4549001455307007},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4414646625518799},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.42008352279663086},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.38678789138793945},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.2554568350315094},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07894173264503479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8411394953727722},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.7588688731193542},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.6432723999023438},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6149227619171143},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.596112847328186},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.5570594668388367},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.530903697013855},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5269219279289246},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5015003681182861},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4936150312423706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4549001455307007},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4414646625518799},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.42008352279663086},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.38678789138793945},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2554568350315094},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07894173264503479},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1807085.1807099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807085.1807099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-ninth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.168.6119","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.168.6119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ust.hk/%7Eyike/pods10-cdsample.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-27427","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-27427","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1521238083","https://openalex.org/W1545349331","https://openalex.org/W1599814229","https://openalex.org/W1970779762","https://openalex.org/W2029538739","https://openalex.org/W2036035006","https://openalex.org/W2054459484","https://openalex.org/W2055721472","https://openalex.org/W2067467757","https://openalex.org/W2082553115","https://openalex.org/W2089297152","https://openalex.org/W2095955605","https://openalex.org/W2107443258","https://openalex.org/W2112452856","https://openalex.org/W2114536330","https://openalex.org/W2119885577","https://openalex.org/W2134743705","https://openalex.org/W2156632255","https://openalex.org/W2157268058","https://openalex.org/W2161317557","https://openalex.org/W2161364365","https://openalex.org/W2166767032","https://openalex.org/W2752908210","https://openalex.org/W3137191742","https://openalex.org/W4238284510"],"related_works":["https://openalex.org/W127192698","https://openalex.org/W2360131081","https://openalex.org/W1572762191","https://openalex.org/W3207785250","https://openalex.org/W2985941356","https://openalex.org/W1994631397","https://openalex.org/W2991818765","https://openalex.org/W2106570241","https://openalex.org/W4360995307","https://openalex.org/W2167004500"],"abstract_inverted_index":{"A":[0],"fundamental":[1],"problem":[2,31],"in":[3,163],"data":[4,14,28,37,60],"management":[5],"is":[6,38,46,52,82],"to":[7,47,66,85,121,134,179,183,190],"draw":[8],"a":[9,12,50,127],"sample":[10,51,128],"of":[11,58,73,139,165],"large":[13],"set,":[15],"for":[16,98,108],"approximate":[17],"query":[18,23],"answering,":[19],"selectivity":[20],"estimation,":[21],"and":[22,70,94,112,133,188],"planning.":[24],"With":[25],"large,":[26],"streaming":[27],"sets,":[29],"this":[30,102],"becomes":[32],"particularly":[33],"difficult":[34],"when":[35,124],"the":[36,56,59,63,68,74,78,87,92,122,130,135,141,149,166],"shared":[39],"across":[40,55],"multiple":[41],"distributed":[42,117],"sites.":[43],"The":[44],"challenge":[45],"ensure":[48],"that":[49,156,171],"drawn":[53],"uniformly":[54],"union":[57],"while":[61],"minimizing":[62],"communication":[64,167],"needed":[65],"run":[67],"protocol":[69,88],"track":[71],"parameters":[72],"evolving":[75],"data.":[76],"At":[77],"same":[79],"time,":[80],"it":[81],"also":[83,170],"necessary":[84],"make":[86],"lightweight,":[89],"by":[90],"keeping":[91],"space":[93,189],"time":[95,152,182],"costs":[96],"low":[97],"each":[99,185],"participant.":[100],"In":[101],"paper,":[103],"we":[104,125],"present":[105],"communication-efficient":[106],"protocols":[107,158],"sampling":[109],"(both":[110],"with":[111],"without":[113],"replacement)":[114],"from":[115,129],"k":[116],"streams.":[118],"These":[119],"apply":[120],"case":[123],"want":[126],"full":[131],"streams,":[132],"sliding":[136],"window":[137],"cases":[138],"only":[140],"W":[142],"most":[143],"recent":[144],"items,":[145],"or":[146,175],"arrivals":[147],"within":[148],"last":[150],"w":[151],"units.":[153],"We":[154],"show":[155],"our":[157],"are":[159],"optimal,":[160],"not":[161],"just":[162],"terms":[164],"used,":[168],"but":[169],"they":[172],"use":[173],"minimal":[174,177],"near":[176],"(up":[178],"logarithmic":[180],"factors)":[181],"process":[184],"new":[186],"item,":[187],"operate.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":15}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}