{"id":"https://openalex.org/W4411403539","doi":"https://doi.org/10.1145/3725336","title":"PLM4NDV: Minimizing Data Access for Number of Distinct Values Estimation with Pre-trained Language Models","display_name":"PLM4NDV: Minimizing Data Access for Number of Distinct Values Estimation with Pre-trained Language Models","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411403539","doi":"https://doi.org/10.1145/3725336"},"language":"en","primary_location":{"id":"doi:10.1145/3725336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725336","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725336","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3725336","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082368205","display_name":"Xianghong Xu","orcid":"https://orcid.org/0000-0003-2447-4107"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianghong Xu","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2447-4107","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","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"],"raw_orcid":"https://orcid.org/0000-0001-7959-2157","affiliations":[{"raw_affiliation_string":"ByteDance, Hangzhou, 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"],"raw_orcid":"https://orcid.org/0009-0003-2250-5528","affiliations":[{"raw_affiliation_string":"Bytedance, San Jose, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048835660","display_name":"Lei Zhang","orcid":"https://orcid.org/0009-0004-1681-1956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["ByteDance, San Jose, USA"],"raw_orcid":"https://orcid.org/0009-0004-1681-1956","affiliations":[{"raw_affiliation_string":"ByteDance, San Jose, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785595","display_name":"Rui Shi","orcid":"https://orcid.org/0009-0003-9122-4703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Shi","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-9122-4703","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100410508","display_name":"Jianjun Chen","orcid":"https://orcid.org/0000-0002-3734-892X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianjun Chen","raw_affiliation_strings":["ByteDance, San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0002-3734-892X","affiliations":[{"raw_affiliation_string":"ByteDance, San Jose, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0938,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79068424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"3","issue":"3","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9739999771118164,"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/T11106","display_name":"Data Management and Algorithms","score":0.9728999733924866,"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/computer-science","display_name":"Computer science","score":0.8048365116119385},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.5598978400230408},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5554076433181763},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.42916885018348694},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42055752873420715},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.31353020668029785},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2932742238044739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8048365116119385},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.5598978400230408},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5554076433181763},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.42916885018348694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42055752873420715},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31353020668029785},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2932742238044739},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3725336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725336","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725336","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2504.00608","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.00608","pdf_url":"https://arxiv.org/pdf/2504.00608","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3725336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725336","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725336","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411403539.pdf","grobid_xml":"https://content.openalex.org/works/W4411403539.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W324611197","https://openalex.org/W1164259208","https://openalex.org/W1601435884","https://openalex.org/W1785933978","https://openalex.org/W1873671735","https://openalex.org/W1965996575","https://openalex.org/W1982092405","https://openalex.org/W1987487696","https://openalex.org/W1992363839","https://openalex.org/W2005731313","https://openalex.org/W2008365755","https://openalex.org/W2012251118","https://openalex.org/W2022257958","https://openalex.org/W2024180465","https://openalex.org/W2025051251","https://openalex.org/W2032421424","https://openalex.org/W2058991275","https://openalex.org/W2064379477","https://openalex.org/W2066865129","https://openalex.org/W2072886604","https://openalex.org/W2087317232","https://openalex.org/W2090415144","https://openalex.org/W2092090135","https://openalex.org/W2114413252","https://openalex.org/W2132823934","https://openalex.org/W2151065878","https://openalex.org/W2153329411","https://openalex.org/W2205512358","https://openalex.org/W2259091399","https://openalex.org/W2351070352","https://openalex.org/W2762763087","https://openalex.org/W2780154280","https://openalex.org/W2963017284","https://openalex.org/W2970641574","https://openalex.org/W2974229142","https://openalex.org/W2976691103","https://openalex.org/W2981852735","https://openalex.org/W3010267622","https://openalex.org/W3014705052","https://openalex.org/W3123375411","https://openalex.org/W3145728363","https://openalex.org/W3185341429","https://openalex.org/W3198659451","https://openalex.org/W3214955223","https://openalex.org/W4210546623","https://openalex.org/W4242142158","https://openalex.org/W4281826654","https://openalex.org/W4288089799","https://openalex.org/W4291124804","https://openalex.org/W4317641440","https://openalex.org/W4365456672","https://openalex.org/W4381326864","https://openalex.org/W4381329189","https://openalex.org/W4385286983","https://openalex.org/W4387559950","https://openalex.org/W4387841511","https://openalex.org/W4387848894","https://openalex.org/W4391054871","https://openalex.org/W4399163413","https://openalex.org/W4399163744","https://openalex.org/W4399175431","https://openalex.org/W4401352024"],"related_works":["https://openalex.org/W2181722423","https://openalex.org/W2347222412","https://openalex.org/W2085601491","https://openalex.org/W2375996887","https://openalex.org/W4322723290","https://openalex.org/W2368976073","https://openalex.org/W2948237757","https://openalex.org/W2376548177","https://openalex.org/W2808994565","https://openalex.org/W2769449614"],"abstract_inverted_index":{"Number":[0],"of":[1,6,22,32,116,129,165],"Distinct":[2],"Values":[3],"(NDV)":[4],"estimation":[5],"a":[7,10,29,95,126,158],"multiset/column":[8],"is":[9,172],"basis":[11],"for":[12,108],"many":[13],"data":[14,50,61,139,153],"management":[15],"tasks,":[16],"especially":[17],"within":[18],"databases.":[19],"Despite":[20],"decades":[21],"research,":[23],"most":[24],"existing":[25],"methods":[26],"require":[27],"either":[28],"significant":[30],"amount":[31],"samples":[33],"through":[34],"uniform":[35],"random":[36],"sampling":[37],"or":[38],"access":[39,51,140],"to":[40,44,48,73,103,124],"the":[41,86,114,117,121,130,135,163],"entire":[42],"column":[43,119],"produce":[45],"estimates,":[46],"leading":[47],"substantial":[49],"costs":[52],"and":[53,120,146],"potentially":[54],"ineffective":[55],"estimations":[56],"in":[57],"scenarios":[58],"with":[59],"limited":[60],"access.":[62,154],"In":[63],"this":[64,90],"paper,":[65],"we":[66,92],"propose":[67,93],"leveraging":[68],"semantic":[69,81,105],"information,":[70],"i.e.,":[71],"schema,":[72],"address":[74],"these":[75],"challenges.":[76],"The":[77],"schema":[78,106],"contains":[79],"rich":[80],"information":[82,107],"that":[83],"can":[84,147],"benefit":[85],"NDV":[87,109,144],"estimation.":[88,110],"To":[89],"end,":[91],"PLM4NDV,":[94],"learned":[96],"method":[97],"incorporating":[98],"Pre-trained":[99],"Language":[100],"Models":[101],"(PLMs)":[102],"extract":[104],"Specifically,":[111],"PLM4NDV":[112,137,166],"leverages":[113],"semantics":[115],"target":[118],"corresponding":[122],"table":[123],"gain":[125],"comprehensive":[127],"understanding":[128],"column's":[131],"meaning.":[132],"By":[133],"using":[134],"semantics,":[136],"reduces":[138],"costs,":[141],"provides":[142],"accurate":[143],"estimation,":[145],"even":[148],"operate":[149],"effectively":[150],"without":[151],"any":[152],"Extensive":[155],"experiments":[156],"on":[157],"large-scale":[159],"real-world":[160],"dataset":[161],"demonstrate":[162],"superiority":[164],"over":[167],"baseline":[168],"methods.":[169],"Our":[170],"code":[171],"available":[173],"at":[174],"https://github.com/bytedance/plm4ndv.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}