{"id":"https://openalex.org/W4409231202","doi":"https://doi.org/10.14778/3712221.3712249","title":"Datamap-Driven Tabular Coreset Selection for Classifier Training","display_name":"Datamap-Driven Tabular Coreset Selection for Classifier Training","publication_year":2024,"publication_date":"2024-11-01","ids":{"openalex":"https://openalex.org/W4409231202","doi":"https://doi.org/10.14778/3712221.3712249"},"language":"en","primary_location":{"id":"doi:10.14778/3712221.3712249","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3712221.3712249","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/A5039498975","display_name":"Adva Hadar","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Aviv Hadar","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110095410","display_name":"Tova Milo","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tova Milo","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044808853","display_name":"Kathy Razmadze","orcid":"https://orcid.org/0000-0002-9165-2025"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Kathy Razmadze","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039498975"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":0.7088,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78433539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"18","issue":"3","first_page":"876","last_page":"888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9987999796867371,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9987999796867371,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9987000226974487,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9973000288009644,"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/classifier","display_name":"Classifier (UML)","score":0.4890182912349701},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4832649827003479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47185584902763367},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43250128626823425},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39499491453170776}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4890182912349701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4832649827003479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47185584902763367},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43250128626823425},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39499491453170776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3712221.3712249","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3712221.3712249","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1505753439","https://openalex.org/W2020018978","https://openalex.org/W2037701287","https://openalex.org/W2045964207","https://openalex.org/W2099964107","https://openalex.org/W2204875540","https://openalex.org/W2342049278","https://openalex.org/W2795530455","https://openalex.org/W2896733135","https://openalex.org/W2903950532","https://openalex.org/W2948791565","https://openalex.org/W2966284335","https://openalex.org/W3031176864","https://openalex.org/W3096831136","https://openalex.org/W3100965700","https://openalex.org/W3103649165","https://openalex.org/W3105982656","https://openalex.org/W3171357976","https://openalex.org/W3174086521","https://openalex.org/W3197431719","https://openalex.org/W3214005765","https://openalex.org/W4231524450","https://openalex.org/W4256300792","https://openalex.org/W4304701435","https://openalex.org/W4309299369","https://openalex.org/W4312929313","https://openalex.org/W4313227433","https://openalex.org/W4319296823","https://openalex.org/W4321448327","https://openalex.org/W6802639663","https://openalex.org/W6845989552","https://openalex.org/W6846669142"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0],"the":[1,46,52,64,88],"era":[2],"of":[3,48,90],"data-driven":[4],"decision-making,":[5],"efficient":[6],"machine":[7,93],"learning":[8,94],"model":[9],"training":[10,57,91],"is":[11],"crucial.":[12],"We":[13],"present":[14],"a":[15,56,73],"novel":[16],"algorithm":[17],"for":[18,26,82],"constructing":[19],"tabular":[20,92],"data":[21],"coresets":[22],"using":[23],"datamaps":[24],"created":[25],"Gradient":[27],"Boosting":[28],"Decision":[29],"Trees":[30],"models.":[31,95],"The":[32],"resulting":[33],"coresets,":[34],"computed":[35],"within":[36],"minutes,":[37],"consistently":[38],"outperform":[39],"other":[40],"baselines":[41],"and":[42,80],"match":[43],"or":[44],"exceed":[45],"performance":[47,68],"models":[49],"trained":[50],"on":[51],"entire":[53],"dataset.":[54],"Additionally,":[55],"enhancement":[58],"method":[59],"leveraging":[60],"datamap":[61],"insights":[62],"during":[63],"inference":[65],"phase":[66],"improves":[67],"with":[69],"mathematical":[70],"guarantees,":[71],"given":[72],"defined":[74],"property":[75],"holds.":[76],"An":[77],"explainability":[78],"layer":[79],"tools":[81],"coreset":[83],"size":[84],"optimization":[85],"further":[86],"enhance":[87],"efficiency":[89]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}