{"id":"https://openalex.org/W2418258478","doi":"https://doi.org/10.1145/3097983.3097999","title":"A Minimal Variance Estimator for the Cardinality of Big Data Set Intersection","display_name":"A Minimal Variance Estimator for the Cardinality of Big Data Set Intersection","publication_year":2017,"publication_date":"2017-08-04","ids":{"openalex":"https://openalex.org/W2418258478","doi":"https://doi.org/10.1145/3097983.3097999","mag":"2418258478"},"language":"en","primary_location":{"id":"doi:10.1145/3097983.3097999","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3097983.3097999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","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/A5018066582","display_name":"Reuven Cohen","orcid":"https://orcid.org/0000-0001-8788-2189"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Reuven Cohen","raw_affiliation_strings":["Technion, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080823001","display_name":"Liran Katzir","orcid":"https://orcid.org/0000-0002-3635-8755"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Liran Katzir","raw_affiliation_strings":["Technion, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022558724","display_name":"Aviv Yehezkel","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Aviv Yehezkel","raw_affiliation_strings":["Technion, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2411,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88808516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9979000091552734,"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/T11719","display_name":"Data Quality and Management","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.8264022469520569},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.7710633277893066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7406282424926758},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6660612225532532},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6086040735244751},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5284920930862427},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5238307118415833},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.450278639793396},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3993709683418274},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1723710298538208},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12993308901786804}],"concepts":[{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.8264022469520569},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.7710633277893066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7406282424926758},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6660612225532532},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6086040735244751},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5284920930862427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5238307118415833},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.450278639793396},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3993709683418274},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1723710298538208},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12993308901786804},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3097983.3097999","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3097983.3097999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W25706487","https://openalex.org/W98727202","https://openalex.org/W1610496399","https://openalex.org/W1612155886","https://openalex.org/W1744451269","https://openalex.org/W1856955241","https://openalex.org/W1984566373","https://openalex.org/W1992363839","https://openalex.org/W2005731313","https://openalex.org/W2025051251","https://openalex.org/W2111806841","https://openalex.org/W2114027169","https://openalex.org/W2126333918","https://openalex.org/W2130873367","https://openalex.org/W2132069633","https://openalex.org/W2140313762","https://openalex.org/W2144982963","https://openalex.org/W2148885851","https://openalex.org/W2152565070","https://openalex.org/W2154096150","https://openalex.org/W2372409997","https://openalex.org/W2418258478","https://openalex.org/W2523826058","https://openalex.org/W2583903344","https://openalex.org/W2951327953","https://openalex.org/W4249446031","https://openalex.org/W4249750499","https://openalex.org/W6679663036","https://openalex.org/W6682678078"],"related_works":["https://openalex.org/W2002177687","https://openalex.org/W2058438338","https://openalex.org/W2019471580","https://openalex.org/W4287880334","https://openalex.org/W2941284322","https://openalex.org/W3122602933","https://openalex.org/W2950038056","https://openalex.org/W1544940847","https://openalex.org/W4231271795","https://openalex.org/W2289285490"],"abstract_inverted_index":{"In":[0,81],"recent":[1],"years":[2],"there":[3],"has":[4],"been":[5],"a":[6,42,86],"growing":[7],"interest":[8,52],"in":[9,45,65,108],"developing":[10],"\"streaming":[11],"algorithms\"":[12],"for":[13,89],"efficient":[14],"processing":[15,36],"and":[16,34,78,116],"querying":[17],"of":[18,41,51,57,110],"continuous":[19],"data":[20,60,76],"streams.":[21,61],"These":[22],"algorithms":[23],"seek":[24],"to":[25],"provide":[26],"accurate":[27],"results":[28],"while":[29],"minimizing":[30],"the":[31,35,39,54,94,111,121],"required":[32],"storage":[33],"time,":[37],"at":[38],"price":[40],"small":[43],"inaccuracy":[44],"their":[46],"output.":[47],"A":[48],"fundamental":[49],"query":[50],"is":[53],"intersection":[55],"size":[56],"two":[58],"big":[59],"This":[62],"problem":[63],"arises":[64],"many":[66],"different":[67],"application":[68],"areas,":[69],"such":[70],"as":[71],"network":[72],"monitoring,":[73],"database":[74],"systems,":[75],"integration":[77],"information":[79],"retrieval.":[80],"this":[82,90,102],"paper":[83],"we":[84],"develop":[85],"new":[87],"algorithm":[88,103],"problem,":[91],"based":[92],"on":[93],"Maximum":[95],"Likelihood":[96],"(ML)":[97],"method.":[98],"We":[99],"show":[100],"that":[101,117],"outperforms":[104],"all":[105],"known":[106],"schemes":[107],"terms":[109],"estimation's":[112],"quality":[113],"(lower":[114],"variance)":[115],"it":[118],"asymptotically":[119],"achieves":[120],"optimal":[122],"variance.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}