{"id":"https://openalex.org/W2883658522","doi":"https://doi.org/10.14778/3231751.3231759","title":"Efficient estimation of inclusion coefficient using hyperloglog sketches","display_name":"Efficient estimation of inclusion coefficient using hyperloglog sketches","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2883658522","doi":"https://doi.org/10.14778/3231751.3231759","mag":"2883658522"},"language":"en","primary_location":{"id":"doi:10.14778/3231751.3231759","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3231751.3231759","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/A5070035154","display_name":"Azade Nazi","orcid":"https://orcid.org/0000-0002-4027-6250"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Azade Nazi","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040297543","display_name":"Bolin Ding","orcid":"https://orcid.org/0000-0003-1535-9692"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bolin Ding","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063257827","display_name":"Vivek Narasayya","orcid":"https://orcid.org/0000-0001-7011-7886"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vivek Narasayya","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038037154","display_name":"Surajit Chaudhuri","orcid":"https://orcid.org/0000-0001-8252-5270"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Surajit Chaudhuri","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070035154"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":0.8357,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78642656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"11","issue":"10","first_page":"1097","last_page":"1109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9943000078201294,"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/estimator","display_name":"Estimator","score":0.8101096153259277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5881038904190063},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.575048565864563},{"id":"https://openalex.org/keywords/inclusion","display_name":"Inclusion (mineral)","score":0.5107824802398682},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.48604685068130493},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4166058897972107},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.410092830657959},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32923394441604614},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.30325865745544434},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28572121262550354},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10008221864700317},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07042470574378967},{"id":"https://openalex.org/keywords/mineralogy","display_name":"Mineralogy","score":0.051395952701568604}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8101096153259277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5881038904190063},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.575048565864563},{"id":"https://openalex.org/C109359841","wikidata":"https://www.wikidata.org/wiki/Q728944","display_name":"Inclusion (mineral)","level":2,"score":0.5107824802398682},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.48604685068130493},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4166058897972107},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.410092830657959},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32923394441604614},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.30325865745544434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28572121262550354},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10008221864700317},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07042470574378967},{"id":"https://openalex.org/C199289684","wikidata":"https://www.wikidata.org/wiki/Q83353","display_name":"Mineralogy","level":1,"score":0.051395952701568604},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3231751.3231759","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3231751.3231759","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W760598031","https://openalex.org/W1506430804","https://openalex.org/W1964312191","https://openalex.org/W1965185568","https://openalex.org/W1979819093","https://openalex.org/W1982092405","https://openalex.org/W1991800036","https://openalex.org/W1992363839","https://openalex.org/W2011737794","https://openalex.org/W2018423671","https://openalex.org/W2025051251","https://openalex.org/W2049898997","https://openalex.org/W2067494918","https://openalex.org/W2099725016","https://openalex.org/W2112129552","https://openalex.org/W2116790080","https://openalex.org/W2119400430","https://openalex.org/W2126848435","https://openalex.org/W2132069633","https://openalex.org/W2140523882","https://openalex.org/W2144982963","https://openalex.org/W2164235862","https://openalex.org/W2182148130","https://openalex.org/W2232417456","https://openalex.org/W2270062199","https://openalex.org/W2394595640","https://openalex.org/W2407551165","https://openalex.org/W2418258478","https://openalex.org/W2594590254","https://openalex.org/W2612399882","https://openalex.org/W2898916015","https://openalex.org/W2912437396","https://openalex.org/W2952367104","https://openalex.org/W6679663036","https://openalex.org/W6693783752"],"related_works":["https://openalex.org/W3185553570","https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4285230481","https://openalex.org/W4385769873","https://openalex.org/W2015759683","https://openalex.org/W4281634296","https://openalex.org/W4319161863","https://openalex.org/W2371687270","https://openalex.org/W2155401483"],"abstract_inverted_index":{"Efficiently":[0],"estimating":[1],"the":[2,6,52,62,65],"inclusion":[3,38],"coefficient":[4,39],"-":[5,19],"fraction":[7],"of":[8,10,64,103],"values":[9],"one":[11],"column":[12,18],"that":[13,44,56],"are":[14],"contained":[15],"in":[16,46],"another":[17],"is":[20],"useful":[21],"for":[22,37],"tasks":[23],"such":[24,73],"as":[25,74],"data":[26,96],"profiling":[27],"and":[28,76,78],"foreign-key":[29],"detection.":[30],"We":[31,60],"present":[32],"a":[33,100],"new":[34],"estimator,":[35],"BML,":[36],"based":[40],"on":[41,70],"Hyperloglog":[42,89],"sketches":[43,90],"results":[45],"significantly":[47],"lower":[48],"error":[49,63],"compared":[50],"to":[51],"state-of-the":[53],"art":[54],"approach":[55],"uses":[57],"Bottom-k":[58],"sketches.":[59],"evaluate":[61],"BML":[66],"estimator":[67],"using":[68,98],"experiments":[69],"industry":[71],"benchmarks":[72],"TPC-H":[75],"TPC-DS,":[77],"several":[79],"real-world":[80],"databases.":[81],"As":[82],"an":[83],"independent":[84],"contribution,":[85],"we":[86],"show":[87],"how":[88],"can":[91],"be":[92],"maintained":[93],"incrementally":[94],"with":[95],"deletions":[97],"only":[99],"constant":[101],"amount":[102],"additional":[104],"memory.":[105]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}