{"id":"https://openalex.org/W6929594047","doi":"https://doi.org/10.48550/arxiv.2505.08318","title":"A Unified Model for Cardinality Estimation by Learning from Data and Queries via Sum-Product Networks","display_name":"A Unified Model for Cardinality Estimation by Learning from Data and Queries via Sum-Product Networks","publication_year":2025,"publication_date":"2025-05-13","ids":{"openalex":"https://openalex.org/W6929594047","doi":"https://doi.org/10.48550/arxiv.2505.08318"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2505.08318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.08318","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2505.08318","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liu, Jiawei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fan, Ju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Ju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Tongyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Tongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zeng, Kai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Jiannan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiannan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Quehuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Quehuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ye, Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Tang, Nan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.6843000054359436,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.6843000054359436,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.04800000041723251,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.017000000923871994,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.8102999925613403},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.694100022315979},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6488000154495239},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5480999946594238},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5185999870300293},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.47850000858306885},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4494999945163727},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.4065999984741211},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.3824000060558319},{"id":"https://openalex.org/keywords/database-theory","display_name":"Database theory","score":0.3578000068664551}],"concepts":[{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.8102999925613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687000036239624},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.694100022315979},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6488000154495239},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5722000002861023},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.423799991607666},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.358599990606308},{"id":"https://openalex.org/C12439846","wikidata":"https://www.wikidata.org/wiki/Q4809258","display_name":"Database theory","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C162500139","wikidata":"https://www.wikidata.org/wiki/Q2835887","display_name":"Estimation of distribution algorithm","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2989070954","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database query","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.28220000863075256},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.24889999628067017},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2451000064611435},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.24469999969005585},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.24240000545978546},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.23849999904632568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23510000109672546},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2321999967098236},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.22949999570846558},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2282000035047531},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.22280000150203705},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.22259999811649323},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2151000052690506}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2505.08318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.08318","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2505.08318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.08318","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5784083604812622}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cardinality":[0],"estimation":[1,31,64,148],"is":[2],"a":[3,50,101],"fundamental":[4],"component":[5],"in":[6,17,42,142],"database":[7,44],"systems,":[8],"crucial":[9],"for":[10,126],"generating":[11],"efficient":[12,124],"execution":[13],"plans.":[14],"Despite":[15],"advancements":[16],"learning-based":[18],"cardinality":[19,147],"estimation,":[20],"existing":[21],"methods":[22],"may":[23],"struggle":[24],"to":[25,139],"simultaneously":[26],"optimize":[27],"the":[28,71,119,127,163],"key":[29,165],"criteria:":[30],"accuracy,":[32],"inference":[33,82],"time,":[34],"and":[35,58,84,114,130,145,159],"storage":[36,86],"overhead,":[37,87],"limiting":[38],"their":[39],"practical":[40],"applicability":[41],"real-world":[43],"environments.":[45],"This":[46,116],"paper":[47,117],"introduces":[48],"QSPN,":[49],"unified":[51],"model":[52],"that":[53,104,155],"integrates":[54],"both":[55,143],"data":[56,68],"distribution":[57,69],"query":[59,94],"workload.":[60],"QSPN":[61,88,99,141,156],"achieves":[62,157],"high":[63],"accuracy":[65],"by":[66,107],"modeling":[67],"using":[70],"simple":[72],"yet":[73],"effective":[74],"Sum-Product":[75],"Network":[76],"(SPN)":[77],"structure.":[78],"To":[79],"ensure":[80],"low":[81],"time":[83],"reduce":[85],"further":[89],"partitions":[90],"columns":[91],"based":[92],"on":[93,162],"access":[95],"patterns.":[96],"We":[97,135],"formalize":[98],"as":[100],"tree-based":[102],"structure":[103],"extends":[105],"SPNs":[106],"introducing":[108],"two":[109],"new":[110],"node":[111],"types:":[112],"QProduct":[113],"QSplit.":[115],"studies":[118],"research":[120],"challenges":[121],"of":[122,133],"developing":[123],"algorithms":[125],"offline":[128],"construction":[129],"online":[131],"computation":[132],"QSPN.":[134],"conduct":[136],"extensive":[137],"experiments":[138],"evaluate":[140],"single-table":[144],"multi-table":[146],"settings.":[149],"The":[150],"experimental":[151],"results":[152],"have":[153],"demonstrated":[154],"superior":[158],"robust":[160],"performance":[161],"three":[164],"criteria,":[166],"compared":[167],"with":[168],"state-of-the-art":[169],"approaches.":[170]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}