{"id":"https://openalex.org/W1973643480","doi":"https://doi.org/10.1145/2745754.2745757","title":"External Memory Stream Sampling","display_name":"External Memory Stream Sampling","publication_year":2015,"publication_date":"2015-05-20","ids":{"openalex":"https://openalex.org/W1973643480","doi":"https://doi.org/10.1145/2745754.2745757","mag":"1973643480"},"language":"en","primary_location":{"id":"doi:10.1145/2745754.2745757","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2745754.2745757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM SIGMOD-SIGACT-SIGAI  Symposium on Principles of Database Systems","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/A5056448481","display_name":"Xiaocheng Hu","orcid":"https://orcid.org/0000-0002-7736-9098"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaocheng Hu","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039191608","display_name":"Miao Qiao","orcid":"https://orcid.org/0000-0001-8374-140X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Miao Qiao","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048609852","display_name":"Yufei Tao","orcid":"https://orcid.org/0000-0003-3883-5452"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yufei Tao","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3507,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66226255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9995999932289124,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9977999925613403,"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":0.7543032169342041},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.6160314083099365},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5510441064834595},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5296401977539062},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.49850988388061523},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4935234785079956},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48424002528190613},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.45366033911705017},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.43435657024383545},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35070037841796875},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3080576956272125},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.19527602195739746},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1477741301059723},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13545921444892883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7543032169342041},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.6160314083099365},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5510441064834595},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5296401977539062},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.49850988388061523},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4935234785079956},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48424002528190613},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.45366033911705017},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.43435657024383545},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35070037841796875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3080576956272125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.19527602195739746},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1477741301059723},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13545921444892883},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2745754.2745757","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2745754.2745757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM SIGMOD-SIGACT-SIGAI  Symposium on Principles of Database Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.716.5615","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.716.5615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://appsrv.cse.cuhk.edu.hk/%7Exchu/paper/pods15-sam.pdf","raw_type":"text"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:607333","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402388","display_name":"Queensland's institutional digital repository (The University of Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1966484605","https://openalex.org/W1969420048","https://openalex.org/W2004110412","https://openalex.org/W2022942700","https://openalex.org/W2031034601","https://openalex.org/W2036035006","https://openalex.org/W2038142281","https://openalex.org/W2068625010","https://openalex.org/W2074613167","https://openalex.org/W2082553115","https://openalex.org/W2088116875","https://openalex.org/W2094308804","https://openalex.org/W2113046370","https://openalex.org/W2113689712","https://openalex.org/W2119885577","https://openalex.org/W2150929954","https://openalex.org/W2158194525","https://openalex.org/W2618200412","https://openalex.org/W3137101798","https://openalex.org/W4247481648"],"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/W2886490431","https://openalex.org/W2360131081","https://openalex.org/W2985941356","https://openalex.org/W4361801939","https://openalex.org/W180351855"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,46,56,83],"understand":[4],"the":[5,15,32,41,85,100],"I/O-complexity":[6],"of":[7,51],"maintaining":[8],"a":[9,19,27,90],"big":[10],"sample":[11],"set---whose":[12],"size":[13],"exceeds":[14],"internal":[16],"memory's":[17],"capacity---on":[18],"data":[20],"stream.":[21],"We":[22],"study":[23],"this":[24],"topic":[25],"in":[26,109,116],"new":[28,101],"computation":[29,93],"model,":[30,37],"named":[31],"external":[33,43],"memory":[34,44],"stream":[35,47,97],"(EMS)":[36],"that":[38,111],"naturally":[39],"extends":[40],"standard":[42],"model":[45,87,94,102],"environments.":[48],"A":[49],"suite":[50],"EMS-indigenous":[52],"techniques":[53],"are":[54],"presented":[55],"prove":[57],"matching":[58],"lower":[59],"and":[60,66,72],"upper":[61],"bounds":[62],"for":[63,95],"with-replacement":[64],"(WR)":[65],"without-replacement":[67],"(WoR)":[68],"sampling":[69],"on":[70],"append-only":[71],"time-based":[73],"sliding":[74],"window":[75],"streams,":[76],"respectively.":[77],"Our":[78],"results":[79],"imply":[80],"that,":[81],"compared":[82],"RAM,":[84],"EMS":[86],"is":[88],"perhaps":[89],"more":[91],"suitable":[92],"studying":[96],"sampling,":[98],"because":[99],"separates":[103],"different":[104],"problems":[105],"by":[106],"their":[107],"hardness":[108],"ways":[110],"could":[112],"not":[113],"be":[114],"observed":[115],"RAM.":[117]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
