{"id":"https://openalex.org/W3173932439","doi":"https://doi.org/10.1145/3448016.3452805","title":"Small Selectivities Matter: Lifting the Burden of Empty Samples","display_name":"Small Selectivities Matter: Lifting the Burden of Empty Samples","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3173932439","doi":"https://doi.org/10.1145/3448016.3452805","mag":"3173932439"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3452805","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3452805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","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/A5063100868","display_name":"Axel Hertzschuch","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Axel Hertzschuch","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025678292","display_name":"Guido Moerkotte","orcid":null},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Guido Moerkotte","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"affiliations":[{"raw_affiliation_string":"University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063512642","display_name":"Wolfgang Lehner","orcid":"https://orcid.org/0000-0001-8107-2775"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Lehner","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040281275","display_name":"Norman May","orcid":"https://orcid.org/0000-0001-9671-0856"},"institutions":[{"id":"https://openalex.org/I4210132444","display_name":"Systems, Applications & Products in Data Processing (Germany)","ror":"https://ror.org/03dsc8d33","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210132444"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Norman May","raw_affiliation_strings":["SAP SE, Walldorf, Germany"],"affiliations":[{"raw_affiliation_string":"SAP SE, Walldorf, Germany","institution_ids":["https://openalex.org/I4210132444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020452978","display_name":"Florian Wolf","orcid":"https://orcid.org/0000-0001-7251-2951"},"institutions":[{"id":"https://openalex.org/I4210132444","display_name":"Systems, Applications & Products in Data Processing (Germany)","ror":"https://ror.org/03dsc8d33","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210132444"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Wolf","raw_affiliation_strings":["SAP SE, Walldorf, Germany"],"affiliations":[{"raw_affiliation_string":"SAP SE, Walldorf, Germany","institution_ids":["https://openalex.org/I4210132444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007677050","display_name":"Lars Fricke","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132444","display_name":"Systems, Applications & Products in Data Processing (Germany)","ror":"https://ror.org/03dsc8d33","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210132444"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lars Fricke","raw_affiliation_strings":["SAP SE, Walldorf, Germany"],"affiliations":[{"raw_affiliation_string":"SAP SE, Walldorf, Germany","institution_ids":["https://openalex.org/I4210132444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063100868"],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67848248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"697","last_page":"709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9993000030517578,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9993000030517578,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9957000017166138,"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/T11106","display_name":"Data Management and Algorithms","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.8169639110565186},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.8028019070625305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.748468279838562},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.738312840461731},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.6879744529724121},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.673358678817749},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5644623637199402},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5610236525535583},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.510592520236969},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4853929281234741},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4805870056152344},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4732259511947632},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39121103286743164},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2797132134437561},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.184645414352417}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8169639110565186},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8028019070625305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748468279838562},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.738312840461731},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.6879744529724121},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.673358678817749},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5644623637199402},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5610236525535583},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.510592520236969},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4853929281234741},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4805870056152344},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4732259511947632},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39121103286743164},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2797132134437561},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.184645414352417},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3448016.3452805","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3452805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:61158","is_oa":false,"landing_page_url":"https://madoc.bib.uni-mannheim.de/61158/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196315","display_name":"MADOC (University of Mannheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177802217","host_organization_name":"University of Mannheim","host_organization_lineage":["https://openalex.org/I177802217"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G884813875","display_name":null,"funder_award_id":"GRK 1907","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1481552467","https://openalex.org/W1581547316","https://openalex.org/W2022858489","https://openalex.org/W2026966899","https://openalex.org/W2029604816","https://openalex.org/W2034681107","https://openalex.org/W2037192958","https://openalex.org/W2046941888","https://openalex.org/W2056411324","https://openalex.org/W2060883486","https://openalex.org/W2075712468","https://openalex.org/W2101207848","https://openalex.org/W2119885577","https://openalex.org/W2120108467","https://openalex.org/W2120176508","https://openalex.org/W2132823934","https://openalex.org/W2143672210","https://openalex.org/W2151310484","https://openalex.org/W2153160273","https://openalex.org/W2396309311","https://openalex.org/W2396727930","https://openalex.org/W2476917595","https://openalex.org/W2500005155","https://openalex.org/W2534032832","https://openalex.org/W2585664214","https://openalex.org/W2752189538","https://openalex.org/W2797602122","https://openalex.org/W2806056912","https://openalex.org/W2808009442","https://openalex.org/W2890276152","https://openalex.org/W2893813411","https://openalex.org/W2939293933","https://openalex.org/W2946026089","https://openalex.org/W2955798121","https://openalex.org/W2970250254","https://openalex.org/W2991530444","https://openalex.org/W3034090036","https://openalex.org/W3120740533","https://openalex.org/W3124277639","https://openalex.org/W3150455880","https://openalex.org/W4243863038","https://openalex.org/W4299841484","https://openalex.org/W6779587530","https://openalex.org/W6793963561","https://openalex.org/W7002050966"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2280422768","https://openalex.org/W2143551613","https://openalex.org/W3143197806","https://openalex.org/W1979740464","https://openalex.org/W4252555497","https://openalex.org/W2138823233","https://openalex.org/W2143345456","https://openalex.org/W2168592511","https://openalex.org/W3013395906"],"abstract_inverted_index":{"Every":[0],"year":[1],"more":[2,4],"and":[3,18,40,94,136],"advanced":[5],"approaches":[6],"to":[7,43,51,70,87,96,116,142,155,160],"cardinality":[8],"estimation":[9,98,148],"are":[10],"published,":[11],"using":[12],"learned":[13],"models":[14],"or":[15],"other":[16],"data":[17,138],"workload":[19],"specific":[20],"synopses.":[21],"In":[22,100],"contrast,":[23],"the":[24,37,58,73],"majority":[25],"of":[26,60,72,122,145],"commercial":[27],"in-memory":[28],"systems":[29],"still":[30],"relies":[31],"on":[32,128,133],"sampling.":[33],"It":[34,113],"is":[35,114],"arguably":[36],"most":[38,46],"general":[39],"easiest":[41],"estimator":[42],"implement.":[44],"While":[45],"methods":[47],"do":[48],"not":[49],"seem":[50],"improve":[52],"much":[53],"over":[54],"sampling-based":[55],"estimators":[56],"in":[57,77,118],"presence":[59],"non-selective":[61],"queries,":[62],"sampling":[63],"struggles":[64],"with":[65,109],"highly":[66],"selective":[67],"queries":[68],"due":[69],"limitations":[71],"sample":[74,81],"size.":[75],"Especially":[76],"situations":[78],"where":[79],"no":[80],"tuple":[82],"qualifies,":[83],"optimizers":[84],"fall":[85],"back":[86],"basic":[88],"heuristics":[89],"that":[90],"ignore":[91],"attribute":[92],"correlations":[93],"lead":[95],"large":[97],"errors.":[99,149],"this":[101],"work,":[102],"we":[103],"present":[104],"a":[105,125],"novel":[106],"approach,":[107],"dealing":[108],"these":[110],"0-Tuple":[111],"Situations.":[112],"ready":[115],"use":[117],"any":[119],"DBMS":[120],"capable":[121],"sampling,":[123],"showing":[124],"negligible":[126],"impact":[127],"optimization":[129],"time.":[130],"Our":[131],"experiments":[132],"real":[134],"world":[135],"synthetic":[137],"sets":[139],"demonstrate":[140],"up":[141],"two":[143],"orders":[144],"magnitude":[146],"reduced":[147],"Enumerating":[150],"single":[151],"filter":[152],"predicates":[153],"according":[154],"our":[156],"estimates":[157],"reveals":[158],"1.3":[159],"1.8":[161],"times":[162],"faster":[163],"query":[164],"responses":[165],"for":[166],"complex":[167],"filters.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}