{"id":"https://openalex.org/W4410543963","doi":"https://doi.org/10.14778/3717755.3717769","title":"AdaNDV: Adaptive Number of Distinct Value Estimation via Learning to Select and Fuse Estimators","display_name":"AdaNDV: Adaptive Number of Distinct Value Estimation via Learning to Select and Fuse Estimators","publication_year":2024,"publication_date":"2024-12-01","ids":{"openalex":"https://openalex.org/W4410543963","doi":"https://doi.org/10.14778/3717755.3717769"},"language":"en","primary_location":{"id":"doi:10.14778/3717755.3717769","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3717755.3717769","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/A5101210951","display_name":"Xianghong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xianghong Xu","raw_affiliation_strings":["ByteDance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101487889","display_name":"Tieying Zhang","orcid":"https://orcid.org/0009-0003-2250-5528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tieying Zhang","raw_affiliation_strings":["ByteDance, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance, San Jose, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101661867","display_name":"Xiao He","orcid":"https://orcid.org/0000-0001-7959-2157"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao He","raw_affiliation_strings":["ByteDance, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036133734","display_name":"Haoyang Li","orcid":"https://orcid.org/0009-0008-8515-7256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyang Li","raw_affiliation_strings":["ByteDance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rong Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Kang","raw_affiliation_strings":["ByteDance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007618051","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0001-6620-5146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["ByteDance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108122298","display_name":"Liang Xu","orcid":"https://orcid.org/0000-0002-8997-8990"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linhui Xu","raw_affiliation_strings":["ByteDance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040306375","display_name":"Zhimin Liang","orcid":"https://orcid.org/0000-0001-5016-4079"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhimin Liang","raw_affiliation_strings":["ByteDance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014313463","display_name":"Shangyu Luo","orcid":"https://orcid.org/0000-0002-6650-8531"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shangyu Luo","raw_affiliation_strings":["ByteDance, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance, San Jose, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000077347","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-6731-822X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["ByteDance, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"ByteDance, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024337919","display_name":"Jianjun Chen","orcid":"https://orcid.org/0009-0001-0015-4494"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianjun Chen","raw_affiliation_strings":["ByteDance, San Jose, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance, San Jose, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5101210951"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3363,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70832171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"18","issue":"4","first_page":"1104","last_page":"1117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9891999959945679,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9891999959945679,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9890999794006348,"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":0.9883000254631042,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.788627028465271},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.7586435079574585},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.6529516577720642},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5268248915672302},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5265324711799622},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38976290822029114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38751649856567383},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.36777263879776},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11691814661026001},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09408342838287354}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.788627028465271},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.7586435079574585},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6529516577720642},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5268248915672302},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5265324711799622},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38976290822029114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38751649856567383},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36777263879776},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11691814661026001},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09408342838287354},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3717755.3717769","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3717755.3717769","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":39,"referenced_works":["https://openalex.org/W1578512165","https://openalex.org/W1601435884","https://openalex.org/W1873671735","https://openalex.org/W1987487696","https://openalex.org/W2022257958","https://openalex.org/W2024180465","https://openalex.org/W2032421424","https://openalex.org/W2058991275","https://openalex.org/W2066865129","https://openalex.org/W2072886604","https://openalex.org/W2087317232","https://openalex.org/W2091158010","https://openalex.org/W2114413252","https://openalex.org/W2132823934","https://openalex.org/W2149427297","https://openalex.org/W2205512358","https://openalex.org/W2259091399","https://openalex.org/W2762763087","https://openalex.org/W2780154280","https://openalex.org/W2898073868","https://openalex.org/W2902365885","https://openalex.org/W2955669675","https://openalex.org/W2963017284","https://openalex.org/W2974229142","https://openalex.org/W2976691103","https://openalex.org/W3010267622","https://openalex.org/W3105136066","https://openalex.org/W3197357906","https://openalex.org/W3214955223","https://openalex.org/W4210546623","https://openalex.org/W4242142158","https://openalex.org/W4282597468","https://openalex.org/W4290928039","https://openalex.org/W4365456672","https://openalex.org/W4385270175","https://openalex.org/W4387559950","https://openalex.org/W4391054929","https://openalex.org/W4399163744","https://openalex.org/W4399175431"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W4243305035","https://openalex.org/W2379407973","https://openalex.org/W2125195795"],"abstract_inverted_index":{"Estimating":[0],"the":[1,33,102,111,127,130,146,167,183],"Number":[2],"of":[3,104,129,169,175,186],"Distinct":[4],"Values":[5],"(NDV)":[6],"is":[7],"fundamental":[8],"for":[9,37,97],"numerous":[10],"data":[11],"management":[12],"tasks,":[13],"especially":[14],"within":[15],"database":[16],"applications.":[17],"However,":[18],"most":[19,34],"existing":[20,57],"works":[21,154],"primarily":[22],"focus":[23],"on":[24,163],"introducing":[25],"new":[26],"statistical":[27],"or":[28],"learned":[29,49,69,123],"estimators,":[30],"while":[31],"identifying":[32],"suitable":[35],"estimator":[36],"a":[38,48,89,116,122,136],"given":[39],"scenario":[40],"remains":[41],"largely":[42],"unexplored.":[43],"Therefore,":[44],"we":[45,65,114],"propose":[46,66],"AdaNDV,":[47],"method":[50],"designed":[51],"to":[52,59,67,71,125,139],"adaptively":[53],"select":[54,80],"and":[55,75,78,95,133],"fuse":[56],"estimators":[58,77,82,132],"address":[60],"this":[61],"issue.":[62],"Specifically,":[63],"(1)":[64],"use":[68],"models":[70],"distinguish":[72],"between":[73],"overestimated":[74],"underestimated":[76],"then":[79,134],"appropriate":[81],"from":[83,152],"each":[84],"category.":[85],"This":[86],"strategy":[87],"provides":[88],"complementary":[90],"perspective":[91],"by":[92],"integrating":[93],"overestimations":[94],"underestimations":[96],"error":[98],"correction,":[99],"thereby":[100],"improving":[101],"accuracy":[103],"NDV":[105],"estimation.":[106],"(2)":[107],"To":[108],"further":[109],"integrate":[110],"estimation":[112],"results,":[113],"introduce":[115],"novel":[117],"fusion":[118],"approach":[119],"that":[120,155],"employs":[121],"model":[124],"predict":[126],"weights":[128],"selected":[131],"applies":[135],"weighted":[137],"sum":[138],"merge":[140],"them.":[141],"By":[142],"combining":[143],"these":[144],"strategies,":[145],"proposed":[147],"AdaNDV":[148],"fundamentally":[149],"distinguishes":[150],"itself":[151],"previous":[153,180],"directly":[156],"estimate":[157],"NDV.":[158],"Moreover,":[159],"extensive":[160],"experiments":[161],"conducted":[162],"real-world":[164],"datasets,":[165],"with":[166],"number":[168],"individual":[170],"columns":[171],"being":[172],"several":[173],"orders":[174],"magnitude":[176],"larger":[177],"than":[178],"in":[179],"studies,":[181],"demonstrate":[182],"superior":[184],"performance":[185],"our":[187],"method.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}