{"id":"https://openalex.org/W4389315103","doi":"https://doi.org/10.14778/3625054.3625059","title":"ShadowAQP: Efficient Approximate Group-by and Join Query via Attribute-Oriented Sample Size Allocation and Data Generation","display_name":"ShadowAQP: Efficient Approximate Group-by and Join Query via Attribute-Oriented Sample Size Allocation and Data Generation","publication_year":2023,"publication_date":"2023-09-01","ids":{"openalex":"https://openalex.org/W4389315103","doi":"https://doi.org/10.14778/3625054.3625059"},"language":"en","primary_location":{"id":"doi:10.14778/3625054.3625059","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3625054.3625059","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/A5052175650","display_name":"Rong Gu","orcid":"https://orcid.org/0000-0002-1565-9997"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Gu","raw_affiliation_strings":["State Key Laboratory for Novel, Software Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel, Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452589","display_name":"Han Li","orcid":"https://orcid.org/0000-0002-4469-2606"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Li","raw_affiliation_strings":["State Key Laboratory for Novel, Software Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel, Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003181030","display_name":"Haipeng Dai","orcid":"https://orcid.org/0000-0003-0545-8187"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Dai","raw_affiliation_strings":["State Key Laboratory for Novel, Software Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel, Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035199892","display_name":"Wenjie Huang","orcid":"https://orcid.org/0000-0002-5502-7476"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Huang","raw_affiliation_strings":["State Key Laboratory for Novel, Software Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel, Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635746","display_name":"Jie Xue","orcid":"https://orcid.org/0000-0001-7015-1988"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Xue","raw_affiliation_strings":["New York University Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University Shanghai","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755573","display_name":"Meng Li","orcid":"https://orcid.org/0000-0001-5764-960X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Li","raw_affiliation_strings":["State Key Laboratory for Novel, Software Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel, Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101513130","display_name":"Jiaqi Zheng","orcid":"https://orcid.org/0000-0001-8403-9655"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Zheng","raw_affiliation_strings":["State Key Laboratory for Novel, Software Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel, Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102577489","display_name":"Haoran Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoran Cai","raw_affiliation_strings":[""],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046763264","display_name":"Yihua Huang","orcid":"https://orcid.org/0000-0003-1806-0936"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Huang","raw_affiliation_strings":["State Key Laboratory for Novel, Software Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel, Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100428808","display_name":"Guihai Chen","orcid":"https://orcid.org/0000-0002-6934-1685"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guihai Chen","raw_affiliation_strings":["State Key Laboratory for Novel, Software Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel, Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3918,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82982964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"16","issue":"13","first_page":"4216","last_page":"4229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.996399998664856,"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":0.996399998664856,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9959999918937683,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.7183852791786194},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.6078459620475769},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6061117053031921},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5627787113189697},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5383836030960083},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5362531542778015},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4974987804889679},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4917285740375519},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.46684062480926514},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.432323157787323},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32867544889450073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17529404163360596},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14073386788368225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13932618498802185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183852791786194},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6078459620475769},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6061117053031921},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5627787113189697},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5383836030960083},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5362531542778015},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4974987804889679},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4917285740375519},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.46684062480926514},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.432323157787323},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32867544889450073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17529404163360596},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14073386788368225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13932618498802185},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3625054.3625059","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3625054.3625059","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W975351372","https://openalex.org/W2034996255","https://openalex.org/W2048204435","https://openalex.org/W2071989194","https://openalex.org/W2103753221","https://openalex.org/W2152029707","https://openalex.org/W2161503451","https://openalex.org/W2620285820","https://openalex.org/W2753088425","https://openalex.org/W2790625403","https://openalex.org/W2896733135","https://openalex.org/W2970851599","https://openalex.org/W2998032620","https://openalex.org/W2998249308","https://openalex.org/W3009210929","https://openalex.org/W3013555795","https://openalex.org/W3089591685","https://openalex.org/W3099158806","https://openalex.org/W3111141572","https://openalex.org/W4206830372"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2978674666","https://openalex.org/W2074430941","https://openalex.org/W2113096305","https://openalex.org/W2580722822","https://openalex.org/W4293088233","https://openalex.org/W2772305933","https://openalex.org/W1486338765"],"abstract_inverted_index":{"Approximate":[0],"query":[1,77,133,144],"processing":[2],"(AQP)":[3],"is":[4],"one":[5],"of":[6,71,105],"the":[7,65,154],"key":[8],"techniques":[9],"to":[10,58,75,140,151],"cope":[11],"with":[12,86,127],"big":[13],"data":[14,52,89,112],"querying":[15],"problem":[16],"on":[17,46,121,137,148],"account":[18],"that":[19],"it":[20],"obtains":[21],"approximate":[22],"answers":[23],"efficiently.":[24],"To":[25,95],"address":[26],"non-trivial":[27],"sample":[28,48,66],"selection":[29],"and":[30,42,51,60,63,91,99,115],"heavy":[31],"sampling":[32,110],"cost":[33],"issues":[34],"in":[35],"AQP,":[36],"we":[37,101],"propose":[38,102],"ShadowAQP,":[39],"an":[40],"efficient":[41],"accurate":[43],"approach":[44],"based":[45],"attribute-oriented":[47],"size":[49,67],"allocation":[50],"generation.":[53],"We":[54,79],"select":[55],"samples":[56],"according":[57],"group-by":[59],"join":[61],"attributes,":[62],"determine":[64],"for":[68],"each":[69],"group":[70],"unique":[72],"value":[73],"combinations":[74],"improve":[76,97],"accuracy.":[78],"design":[80],"a":[81,103],"conditional":[82],"variational":[83],"autoencoder":[84],"model":[85,92],"automatic":[87],"table":[88],"encoding":[90],"update":[93],"strategies.":[94],"further":[96],"accuracy":[98],"efficiency,":[100],"set":[104],"extensions,":[106],"including":[107],"parallel":[108],"multi-round":[109],"aggregation,":[111],"outlier-aware":[113],"sampling,":[114],"dimension":[116],"reduction":[117],"optimization.":[118],"Evaluation":[119],"results":[120],"diversified":[122],"datasets":[123],"show":[124],"that,":[125],"compared":[126],"SOTA":[128],"approaches,":[129],"ShadowAQP":[130],"achieves":[131],"5.8\u00d7":[132],"speed":[134],"performance":[135],"improvement":[136],"average":[138,149],"(up":[139,150],"12.8\u00d7),":[141],"while":[142],"reducing":[143],"error":[145],"by":[146],"74%":[147],"95%)":[152],"at":[153],"same":[155],"time.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}