{"id":"https://openalex.org/W2909607640","doi":"https://doi.org/10.1109/tpds.2018.2865452","title":"Continuously Distinct Sampling over Centralized and Distributed High Speed Data Streams","display_name":"Continuously Distinct Sampling over Centralized and Distributed High Speed Data Streams","publication_year":2018,"publication_date":"2018-08-14","ids":{"openalex":"https://openalex.org/W2909607640","doi":"https://doi.org/10.1109/tpds.2018.2865452","mag":"2909607640"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2865452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2865452","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5102845337","display_name":"Pinghui Wang","orcid":"https://orcid.org/0000-0002-1434-837X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinghui Wang","raw_affiliation_strings":["Xi'an Jiaotong University, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-1434-837X","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369974","display_name":"Xiangyu Wang","orcid":"https://orcid.org/0000-0001-8718-6941"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Wang","raw_affiliation_strings":["Xi'an Jiaotong University, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101516220","display_name":"Jing Tao","orcid":"https://orcid.org/0009-0009-3911-4260"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Tao","raw_affiliation_strings":["Shenzhen Research School, Xi'an Jiaotong University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research School, Xi'an Jiaotong University, Shenzhen, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949155","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0001-7721-2675"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Xi'an Jiaotong University, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-7721-2675","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075845093","display_name":"Xiaohong Guan","orcid":"https://orcid.org/0000-0002-8826-0362"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohong Guan","raw_affiliation_strings":["Tsinghua National Lab for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Lab for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7582,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76333164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"30","issue":"2","first_page":"300","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9986000061035156,"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/T11478","display_name":"Caching and Content Delivery","score":0.9986000061035156,"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":0.996999979019165,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9959999918937683,"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":0.8514974117279053},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6957986950874329},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.6840472221374512},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.5475072860717773},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5124190449714661},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4903269112110138},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4693276286125183},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4653265178203583},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.43283793330192566},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4250662922859192},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3767995834350586},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3496916890144348},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22425180673599243},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.1089409589767456},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09197309613227844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514974117279053},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6957986950874329},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.6840472221374512},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.5475072860717773},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5124190449714661},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4903269112110138},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4693276286125183},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4653265178203583},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.43283793330192566},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4250662922859192},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3767995834350586},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3496916890144348},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22425180673599243},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.1089409589767456},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09197309613227844},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2018.2865452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2865452","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.7900000214576721,"display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G2453883782","display_name":null,"funder_award_id":"61603290","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G384056880","display_name":"\u8f6f\u4ef6\u5b9a\u4e49\u7684\u7f51\u7edc\u6545\u969c\u8bca\u65ad\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61772412","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G44732868","display_name":null,"funder_award_id":"61602371","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5305885751","display_name":null,"funder_award_id":"U1301254","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6523492929","display_name":null,"funder_award_id":"2015M582663","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8241264154","display_name":null,"funder_award_id":"SBK2014021758","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327721","display_name":"K. C. Wong Education Foundation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W73629738","https://openalex.org/W1499549173","https://openalex.org/W1551652843","https://openalex.org/W1593168739","https://openalex.org/W1858168446","https://openalex.org/W1966127114","https://openalex.org/W1977141583","https://openalex.org/W1977951613","https://openalex.org/W1998071119","https://openalex.org/W1999952442","https://openalex.org/W2002576896","https://openalex.org/W2003496171","https://openalex.org/W2010582541","https://openalex.org/W2010973140","https://openalex.org/W2021681605","https://openalex.org/W2026032151","https://openalex.org/W2031082424","https://openalex.org/W2031657002","https://openalex.org/W2037536649","https://openalex.org/W2040396273","https://openalex.org/W2042112623","https://openalex.org/W2058358261","https://openalex.org/W2058446729","https://openalex.org/W2077599515","https://openalex.org/W2086058820","https://openalex.org/W2094308804","https://openalex.org/W2098366185","https://openalex.org/W2099220942","https://openalex.org/W2102481563","https://openalex.org/W2109885200","https://openalex.org/W2119885577","https://openalex.org/W2124450885","https://openalex.org/W2127455097","https://openalex.org/W2134519279","https://openalex.org/W2134786002","https://openalex.org/W2136987366","https://openalex.org/W2139076222","https://openalex.org/W2140591663","https://openalex.org/W2141390805","https://openalex.org/W2141441292","https://openalex.org/W2142099410","https://openalex.org/W2143439191","https://openalex.org/W2147776030","https://openalex.org/W2150399692","https://openalex.org/W2154191591","https://openalex.org/W2154956479","https://openalex.org/W2157011656","https://openalex.org/W2158432527","https://openalex.org/W2159279931","https://openalex.org/W2161570458","https://openalex.org/W2162826379","https://openalex.org/W2168305032","https://openalex.org/W2169927847","https://openalex.org/W2199464493","https://openalex.org/W2278390984","https://openalex.org/W2305788608","https://openalex.org/W2415869477","https://openalex.org/W2439904216","https://openalex.org/W2443728350","https://openalex.org/W2554164694","https://openalex.org/W2577957252","https://openalex.org/W2605823630","https://openalex.org/W2607280777","https://openalex.org/W2743723076","https://openalex.org/W2775352277","https://openalex.org/W2800198128","https://openalex.org/W2950763147","https://openalex.org/W4206137901","https://openalex.org/W4232254113","https://openalex.org/W4241915340","https://openalex.org/W4372046852","https://openalex.org/W6639080731","https://openalex.org/W6679775555","https://openalex.org/W6698379459","https://openalex.org/W6764055296","https://openalex.org/W6822210576"],"related_works":["https://openalex.org/W4389449520","https://openalex.org/W127192698","https://openalex.org/W2570600173","https://openalex.org/W2893008024","https://openalex.org/W2743735673","https://openalex.org/W4361801939","https://openalex.org/W2360131081","https://openalex.org/W2985941356","https://openalex.org/W2802243998","https://openalex.org/W1521014365"],"abstract_inverted_index":{"Distinct":[0],"sampling":[1],"is":[2,52,68],"fundamental":[3],"for":[4],"computing":[5],"statistics":[6],"(e.g.,":[7,27],"the":[8,22,46,65,71,162,170],"age":[9],"and":[10,33,76,95,109,120,161,167,173],"gender":[11],"distribution":[12],"of":[13,24,42,49,73,79,102,146,176],"distinct":[14,25,107],"users":[15],"accessing":[16],"a":[17,31,40,90,100,135],"particular":[18],"website)":[19],"depending":[20],"on":[21,158],"set":[23,72],"keys":[26,75,108],"user":[28],"IDs)":[29],"in":[30,64,70],"large":[32],"high":[34,54],"speed":[35],"data":[36,66,130,143],"stream":[37,67],"such":[38],"as":[39],"sequence":[41],"key-update":[43,116,147],"pairs.":[44],"However,":[45],"major":[47],"shortcoming":[48],"existing":[50],"methods":[51,178],"their":[53,110],"computational":[55],"cost":[56],"incurred":[57],"by":[58,179],"determining":[59],"whether":[60],"each":[61,115],"incoming":[62],"key":[63],"currently":[69],"sampled":[74,80],"keeping":[77],"track":[78],"keys\u2019":[81],"update":[82,111],"aggregations.":[83,112],"To":[84],"solve":[85],"this":[86],"challenge,":[87],"we":[88,132],"develop":[89,134],"new":[91],"method":[92,137],"<i>random":[93],"projection":[94],"eviction</i>":[96],"(RPE)":[97],"that":[98,165],"uses":[99],"list":[101],"buckets":[103],"to":[104,139],"continuously":[105],"sample":[106],"RPE":[113,166],"processes":[114],"pair":[117],"with":[118,141],"small":[119],"nearly":[121],"constant":[122],"time":[123],"complexity":[124],"<inline-formula><tex-math":[125],"notation=\"LaTeX\">$O(1)$</tex-math></inline-formula>":[126],".":[127],"Besides":[128],"centralized":[129],"streams,":[131],"also":[133],"novel":[136],"DRPE":[138,168],"deal":[140],"distributed":[142,152],"streams":[144],"consisting":[145],"pairs":[148],"observed":[149],"at":[150],"multiple":[151],"sites.":[153],"We":[154],"conduct":[155],"extensive":[156],"experiments":[157],"real-world":[159],"datasets,":[160],"results":[163],"demonstrate":[164],"reduce":[169],"memory,":[171],"computational,":[172],"message":[174],"costs":[175],"state-of-the-art":[177],"several":[180],"times.":[181]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}