{"id":"https://openalex.org/W2135417552","doi":"https://doi.org/10.1109/infcom.2011.5935005","title":"Optimal sampling algorithms for frequency estimation in distributed data","display_name":"Optimal sampling algorithms for frequency estimation in distributed data","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2135417552","doi":"https://doi.org/10.1109/infcom.2011.5935005","mag":"2135417552"},"language":"en","primary_location":{"id":"doi:10.1109/infcom.2011.5935005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcom.2011.5935005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Proceedings IEEE INFOCOM","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/A5062549536","display_name":"Zengfeng Huang","orcid":"https://orcid.org/0000-0003-2671-7483"},"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":true,"raw_author_name":"Zengfeng Huang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"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":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101877973","display_name":"Yunhao Liu","orcid":"https://orcid.org/0000-0001-8052-9200"},"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":"Yunhao Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062549536"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":3.5086,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93178707,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1997","last_page":"2005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.998199999332428,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.998199999332428,"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/T12288","display_name":"Optimization and Search Problems","score":0.9962999820709229,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9902999997138977,"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/multiset","display_name":"Multiset","score":0.8811893463134766},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.7199605703353882},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6948506832122803},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6325125098228455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6035494208335876},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5430587530136108},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28547853231430054},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.22187548875808716},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2101334035396576},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.1860412061214447}],"concepts":[{"id":"https://openalex.org/C2779623528","wikidata":"https://www.wikidata.org/wiki/Q864377","display_name":"Multiset","level":2,"score":0.8811893463134766},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.7199605703353882},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6948506832122803},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6325125098228455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6035494208335876},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5430587530136108},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28547853231430054},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.22187548875808716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2101334035396576},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.1860412061214447},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/infcom.2011.5935005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcom.2011.5935005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Proceedings IEEE INFOCOM","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.224.3374","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.224.3374","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/%7Ehuangzf/infocom11.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.718.9236","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.718.9236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.nju.edu.cn/gchen/newpaper/UploadFiles/infocom2011-keyi.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-44294","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-44294","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W139562302","https://openalex.org/W1483763945","https://openalex.org/W1544095808","https://openalex.org/W1703904868","https://openalex.org/W1967162653","https://openalex.org/W1970779762","https://openalex.org/W1991417304","https://openalex.org/W2018989507","https://openalex.org/W2029146455","https://openalex.org/W2029538739","https://openalex.org/W2069980026","https://openalex.org/W2080234606","https://openalex.org/W2089297152","https://openalex.org/W2089419727","https://openalex.org/W2116400826","https://openalex.org/W2134743705","https://openalex.org/W2141487143","https://openalex.org/W2156632255","https://openalex.org/W2161118867","https://openalex.org/W2162139064","https://openalex.org/W2173213060","https://openalex.org/W2666600683","https://openalex.org/W4238284510","https://openalex.org/W6628994040"],"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/W2128746232","https://openalex.org/W2805443446","https://openalex.org/W4378765295","https://openalex.org/W2005152920","https://openalex.org/W3169136406"],"abstract_inverted_index":{"Consider":[0],"a":[1,11,34,52,101,151],"distributed":[2,153],"system":[3],"with":[4,33,133],"n":[5,81],"nodes":[6],"where":[7,39],"each":[8],"node":[9],"holds":[10],"multiset":[12],"of":[13,30,37,45,55,72,95,121],"items.":[14],"In":[15,88],"this":[16],"paper,":[17],"we":[18,90,125],"design":[19,108],"sampling":[20,104],"algorithms":[21,50,109,132,142],"that":[22,92,110],"allow":[23],"us":[24],"to":[25],"estimate":[26],"the":[27,42,63,114,138],"global":[28],"frequency":[29],"any":[31],"item":[32],"standard":[35],"deviation":[36],"\u03b5N,":[38],"N":[40],"denotes":[41],"total":[43],"cardinality":[44],"all":[46],"these":[47],"multisets.":[48],"Our":[49],"have":[51],"communication":[53],"cost":[54,71],"O(n":[56,64],"+\u221an/\u03b5),":[57],"which":[58],"is":[59,98],"never":[60],"worse":[61],"than":[62,137],"+":[65],"1/\u03b5":[66,83],"<sup":[67,84],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[68,85],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[69,86],")":[70],"uniform":[73],"sampling,":[74],"and":[75,147],"could":[76],"be":[77],"much":[78,145],"better":[79],"when":[80],"\u226a":[82],".":[87],"addition,":[89],"prove":[91],"one":[93],"version":[94],"our":[96,131,141],"algorithm":[97],"instance-optimal":[99],"in":[100,150],"fairly":[102],"general":[103],"framework.":[105],"We":[106],"also":[107,144],"achieve":[111],"optimality":[112],"on":[113],"bit":[115],"level,":[116],"by":[117],"combining":[118],"Bloom":[119],"filters":[120],"various":[122],"granularities.":[123],"Finally,":[124],"present":[126],"some":[127],"simulation":[128],"results":[129],"comparing":[130],"previous":[134],"techniques.":[135],"Other":[136],"performance":[139],"improvement,":[140],"are":[143],"simpler":[146],"easily":[148],"implementable":[149],"large-scale":[152],"system.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}