{"id":"https://openalex.org/W2018989507","doi":"https://doi.org/10.14778/1454159.1454225","title":"Finding frequent items in data streams","display_name":"Finding frequent items in data streams","publication_year":2008,"publication_date":"2008-08-01","ids":{"openalex":"https://openalex.org/W2018989507","doi":"https://doi.org/10.14778/1454159.1454225","mag":"2018989507"},"language":"en","primary_location":{"id":"doi:10.14778/1454159.1454225","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1454159.1454225","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/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"],"raw_orcid":null,"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/A5058831095","display_name":"Marios Hadjieleftheriou","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":"Marios Hadjieleftheriou","raw_affiliation_strings":["AT&T Labs-Research, Florham Park, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":49.9152,"has_fulltext":false,"cited_by_count":308,"citation_normalized_percentile":{"value":0.99811237,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"1","issue":"2","first_page":"1530","last_page":"1541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9973000288009644,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/implementation","display_name":"Implementation","score":0.8592139482498169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7229428291320801},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5678554177284241},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.5465684533119202},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5327420830726624},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5278382301330566},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.5196791291236877},{"id":"https://openalex.org/keywords/streams","display_name":"STREAMS","score":0.49832868576049805},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.4948241114616394},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4537146985530853},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18579843640327454},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10751068592071533},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08205318450927734}],"concepts":[{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.8592139482498169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229428291320801},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5678554177284241},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.5465684533119202},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5327420830726624},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5278382301330566},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.5196791291236877},{"id":"https://openalex.org/C42090638","wikidata":"https://www.wikidata.org/wiki/Q4048907","display_name":"STREAMS","level":2,"score":0.49832868576049805},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.4948241114616394},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4537146985530853},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18579843640327454},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10751068592071533},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08205318450927734},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/1454159.1454225","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1454159.1454225","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:10.1.1.140.8304","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.8304","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/1/1454225.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.145.8413","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.145.8413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.att.com/~marioh/papers/vldb08-2.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2540670","https://openalex.org/W31696346","https://openalex.org/W1489091404","https://openalex.org/W1493892051","https://openalex.org/W1525132895","https://openalex.org/W1553409264","https://openalex.org/W1601184934","https://openalex.org/W1634257591","https://openalex.org/W1675727887","https://openalex.org/W1766932551","https://openalex.org/W1977951613","https://openalex.org/W2004110412","https://openalex.org/W2004154913","https://openalex.org/W2006355640","https://openalex.org/W2026784425","https://openalex.org/W2039852170","https://openalex.org/W2049282244","https://openalex.org/W2050290319","https://openalex.org/W2058858139","https://openalex.org/W2064379477","https://openalex.org/W2069980026","https://openalex.org/W2075567379","https://openalex.org/W2080234606","https://openalex.org/W2112452856","https://openalex.org/W2113139394","https://openalex.org/W2119714163","https://openalex.org/W2122529145","https://openalex.org/W2126922390","https://openalex.org/W2130297445","https://openalex.org/W2150569458","https://openalex.org/W2152637787","https://openalex.org/W2154096150","https://openalex.org/W2161118867","https://openalex.org/W2166290564","https://openalex.org/W2170963089","https://openalex.org/W2188351697","https://openalex.org/W2562755098","https://openalex.org/W2621193479","https://openalex.org/W6600089937","https://openalex.org/W6601321837","https://openalex.org/W6629496199","https://openalex.org/W6660346676","https://openalex.org/W6678120442"],"related_works":["https://openalex.org/W2313030483","https://openalex.org/W2067164079","https://openalex.org/W2334651808","https://openalex.org/W2106570241","https://openalex.org/W2366772082","https://openalex.org/W2039848804","https://openalex.org/W1582424504","https://openalex.org/W2378640446","https://openalex.org/W1518573110","https://openalex.org/W2358793424"],"abstract_inverted_index":{"The":[0,152],"frequent":[1,51,149,160],"items":[2,10,14,150,161,177],"problem":[3,111],"is":[4,25,79,93,142],"to":[5,39,81,103,127,158],"process":[6],"a":[7,18,113,129],"stream":[8,35],"of":[9,21,27,70,121,133,148,168,170,174,176],"and":[11,53,124],"find":[12,82,159],"all":[13],"occurring":[15],"more":[16],"than":[17],"given":[19],"fraction":[20],"the":[22,28,40,50,71,105,122,146],"time.":[23],"It":[24,78],"one":[26],"most":[29,106],"heavily":[30],"studied":[31],"problems":[32],"in":[33,56,58,88,112,145],"data":[34],"mining,":[36],"dating":[37],"back":[38],"1980s.":[41],"Many":[42],"applications":[43],"rely":[44],"directly":[45],"or":[46,96],"indirectly":[47],"on":[48,85,180],"finding":[49],"items,":[52],"implementations":[54,120],"are":[55],"use":[57],"large":[59],"scale":[60],"industrial":[61],"systems.":[62],"However,":[63],"there":[64,141],"has":[65],"not":[66],"been":[67],"much":[68],"comparison":[69],"different":[72],"methods":[73,154],"under":[74],"uniform":[75],"experimental":[76,131],"conditions.":[77],"common":[80,114],"papers":[83],"touching":[84],"this":[86,99,110],"topic":[87],"which":[89],"important":[90,107],"related":[91],"work":[92],"mischaracterized,":[94],"overlooked,":[95],"reinvented.":[97],"In":[98],"paper,":[100],"we":[101],"aim":[102],"present":[104],"algorithms":[108],"for":[109],"framework.":[115],"We":[116,136],"have":[117],"created":[118],"baseline":[119],"algorithms,":[123],"used":[125],"these":[126],"perform":[128],"thorough":[130],"study":[132],"their":[134],"properties.":[135],"give":[137],"empirical":[138],"evidence":[139],"that":[140],"considerable":[143],"variation":[144],"performance":[147],"algorithms.":[151],"best":[153],"can":[155],"be":[156],"implemented":[157],"with":[162],"high":[163],"accuracy":[164],"using":[165],"only":[166],"tens":[167],"kilobytes":[169],"memory,":[171],"at":[172],"rates":[173],"millions":[175],"per":[178],"second":[179],"cheap":[181],"modern":[182],"hardware.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":28},{"year":2017,"cited_by_count":26},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":26},{"year":2012,"cited_by_count":13}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}