{"id":"https://openalex.org/W4226186506","doi":"https://doi.org/10.1007/s13222-021-00400-z","title":"Aggregate-based Training Phase for ML-based Cardinality Estimation","display_name":"Aggregate-based Training Phase for ML-based Cardinality Estimation","publication_year":2022,"publication_date":"2022-01-10","ids":{"openalex":"https://openalex.org/W4226186506","doi":"https://doi.org/10.1007/s13222-021-00400-z"},"language":"en","primary_location":{"id":"doi:10.1007/s13222-021-00400-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-021-00400-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-021-00400-z.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s13222-021-00400-z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077087558","display_name":"Lucas Woltmann","orcid":"https://orcid.org/0000-0003-0720-8878"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lucas Woltmann","raw_affiliation_strings":["Dresden Database Research Group, Technische Universit\u00e4t Dresden, Dresden, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0720-8878","affiliations":[{"raw_affiliation_string":"Dresden Database Research Group, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034533320","display_name":"Claudio Hartmann","orcid":"https://orcid.org/0000-0002-5334-059X"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudio Hartmann","raw_affiliation_strings":["Dresden Database Research Group, Technische Universit\u00e4t Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dresden Database Research Group, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057703543","display_name":"Dirk Habich","orcid":"https://orcid.org/0000-0002-8671-5466"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dirk Habich","raw_affiliation_strings":["Dresden Database Research Group, Technische Universit\u00e4t Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dresden Database Research Group, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","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":"Technische Universit\u00e4t 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":["Dresden Database Research Group, Technische Universit\u00e4t Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dresden Database Research Group, Technische Universit\u00e4t Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077087558"],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":{"value":2380,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2380,"currency":"EUR","value_usd":2890},"fwci":0.4457,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56428869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"22","issue":"1","first_page":"45","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980000257492065,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.80921471118927},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.757199764251709},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.7081903219223022},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6511044502258301},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5598515272140503},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.5239170789718628},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4726002812385559},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41824156045913696},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3963695764541626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35353171825408936},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.09803566336631775},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07541298866271973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80921471118927},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.757199764251709},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.7081903219223022},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6511044502258301},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5598515272140503},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5239170789718628},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4726002812385559},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41824156045913696},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3963695764541626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35353171825408936},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.09803566336631775},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07541298866271973},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s13222-021-00400-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-021-00400-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-021-00400-z.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2005.09367","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09367","pdf_url":"https://arxiv.org/pdf/2005.09367","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"doi:10.1007/s13222-021-00400-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-021-00400-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-021-00400-z.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321613","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226186506.pdf","grobid_xml":"https://content.openalex.org/works/W4226186506.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W201801013","https://openalex.org/W1487902141","https://openalex.org/W1522055873","https://openalex.org/W2008289941","https://openalex.org/W2097067389","https://openalex.org/W2132823934","https://openalex.org/W2145829184","https://openalex.org/W2164399715","https://openalex.org/W2396309311","https://openalex.org/W2396727930","https://openalex.org/W2402498022","https://openalex.org/W2407123212","https://openalex.org/W2604606554","https://openalex.org/W2792538726","https://openalex.org/W2890276152","https://openalex.org/W2910328769","https://openalex.org/W2911464154","https://openalex.org/W2939293933","https://openalex.org/W2946026089","https://openalex.org/W2950461515","https://openalex.org/W2962771342","https://openalex.org/W2998249308","https://openalex.org/W3105457604","https://openalex.org/W3139931056","https://openalex.org/W3198307109","https://openalex.org/W4241830353","https://openalex.org/W4242142158","https://openalex.org/W4248008732","https://openalex.org/W4289258943","https://openalex.org/W4298089263"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W4319452359"],"abstract_inverted_index":{"Abstract":[0],"Cardinality":[1],"estimation":[2,124],"is":[3,90],"a":[4,32,48,93,116],"fundamental":[5],"task":[6],"in":[7,15,76,126,138],"database":[8],"query":[9,71],"processing":[10],"and":[11,73,100,156],"optimization.":[12],"As":[13,129],"shown":[14],"recent":[16],"papers,":[17],"machine":[18],"learning":[19],"(ML)-based":[20],"approaches":[21,125],"may":[22],"deliver":[23],"more":[24],"accurate":[25],"cardinality":[26,123],"estimations":[27],"than":[28],"traditional":[29],"approaches.":[30],"However,":[31],"lot":[33],"of":[34,57,96,149],"training":[35,44,59,85,119,154],"queries":[36,62,105],"have":[37,68],"to":[38,46,91,101,133,144],"be":[39],"executed":[40],"during":[41],"the":[42,64,69,83,97,103],"model":[43,51,84],"phase":[45,120,155],"learn":[47],"data-dependent":[49],"ML":[50],"making":[52],"it":[53],"very":[54],"time-consuming.":[55],"Many":[56],"those":[58],"or":[60],"example":[61,104],"use":[63],"same":[65,70],"base":[66,98],"data,":[67],"structure,":[72],"only":[74],"differ":[75],"their":[77],"selective":[78],"predicates.":[79],"To":[80],"speed":[81],"up":[82],"phase,":[86],"our":[87,139,152],"core":[88],"idea":[89],"determine":[92],"predicate-independent":[94],"pre-aggregation":[95],"data":[99],"execute":[102],"over":[106],"this":[107,112,127],"pre-aggregated":[108],"data.":[109],"Based":[110],"on":[111],"idea,":[113],"we":[114,130,141],"present":[115],"specific":[117],"aggregate-based":[118,153],"for":[121],"ML-based":[122],"paper.":[128],"are":[131,142],"going":[132],"show":[134],"with":[135,151],"different":[136],"workloads":[137],"evaluation,":[140],"able":[143],"achieve":[145],"an":[146],"average":[147],"speedup":[148],"90":[150],"thus":[157],"outperform":[158],"indexes.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}