{"id":"https://openalex.org/W3034656463","doi":"https://doi.org/10.48550/arxiv.2006.07100","title":"Reinforced Data Sampling for Model Diversification","display_name":"Reinforced Data Sampling for Model Diversification","publication_year":2020,"publication_date":"2020-06-12","ids":{"openalex":"https://openalex.org/W3034656463","doi":"https://doi.org/10.48550/arxiv.2006.07100","mag":"3034656463"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2006.07100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.07100","pdf_url":"https://arxiv.org/pdf/2006.07100","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.07100","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101843337","display_name":"Hoang D. Nguyen","orcid":"https://orcid.org/0000-0003-2541-3269","observed_orcids":["https://orcid.org/0000-0003-2541-3269"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Hoang D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028720787","display_name":"Xuan-Son Vu","orcid":"https://orcid.org/0000-0001-8820-2405","observed_orcids":["https://orcid.org/0000-0001-8820-2405"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vu, Xuan-Son","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022545572","display_name":"Quoc-Tuan Truong","orcid":"https://orcid.org/0000-0003-2291-1385","observed_orcids":["https://orcid.org/0000-0003-2291-1385"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Truong, Quoc-Tuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101555110","display_name":"Duc-Trong Le","orcid":"https://orcid.org/0000-0003-4621-8956","observed_orcids":["https://orcid.org/0000-0003-4621-8956"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, Duc-Trong","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":5,"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":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9663000106811523,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9663000106811523,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.013899999670684338,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.004000000189989805,"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/dataset-selection","display_name":"data selection","score":0.7919999957084656},{"id":"https://openalex.org/keywords/concept-drift","display_name":"concept drift","score":0.9990000128746033},{"id":"https://openalex.org/keywords/soft-voting","display_name":"soft voting","score":0.9610000252723694},{"id":"https://openalex.org/keywords/stochastic-choice","display_name":"stochastic choice","score":0.9470000267028809},{"id":"https://openalex.org/keywords/value-function","display_name":"value function","score":0.5669999718666077},{"id":"https://openalex.org/keywords/machine-learning-competition","display_name":"machine learning competition","score":0.6830000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449041604995728},{"id":"https://openalex.org/C180916674","wikidata":"https://www.wikidata.org/wiki/Q3711935","display_name":"Diversification (marketing strategy)","level":2,"score":0.6925164461135864},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6735287308692932},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6559427976608276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5745083093643188},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.570429265499115},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44265392422676086},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.4378354847431183},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36396363377571106},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2006.07100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.07100","pdf_url":"https://arxiv.org/pdf/2006.07100","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2006.07100","doi":"https://doi.org/10.48550/arxiv.2006.07100","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.07100","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,"listed_in":[],"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":"pmh:oai:arXiv.org:2006.07100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.07100","pdf_url":"https://arxiv.org/pdf/2006.07100","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,"listed_in":[],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.4099999964237213,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2000510052","https://openalex.org/W2001150023","https://openalex.org/W2107741520","https://openalex.org/W2139327121","https://openalex.org/W2140879111","https://openalex.org/W2151023586","https://openalex.org/W2151225423","https://openalex.org/W2152799677","https://openalex.org/W2155027007","https://openalex.org/W2171809276","https://openalex.org/W2752853835","https://openalex.org/W2798859316","https://openalex.org/W2891714643","https://openalex.org/W2952566282","https://openalex.org/W2963238274","https://openalex.org/W2963341956","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W2349635380","https://openalex.org/W4353089801","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W2389866386","https://openalex.org/W2905116230"],"abstract_inverted_index":{"With":[0],"the":[1,8,16,20,42,65,74,98,118,152,167],"rising":[2],"number":[3],"of":[4,44,77,100,121,154,186],"machine":[5,188],"learning":[6,86,189],"competitions,":[7],"world":[9],"has":[10],"witnessed":[11],"an":[12],"exciting":[13],"race":[14],"for":[15,67,170,175],"best":[17],"algorithms.":[18],"However,":[19],"involved":[21],"data":[22,62,82,122],"selection":[23,119],"process":[24,120],"may":[25],"fundamentally":[26],"suffer":[27],"from":[28],"evidence":[29],"ambiguity":[30],"and":[31,70,88,136,194],"concept":[32],"drift":[33],"issues,":[34],"thereby":[35],"possibly":[36],"leading":[37],"to":[38,57,60,84,116,139,182],"deleterious":[39],"effects":[40],"on":[41,64,147],"performance":[43],"various":[45,187],"models.":[46],"This":[47,95],"paper":[48],"proposes":[49],"a":[50],"new":[51],"Reinforced":[52],"Data":[53],"Sampling":[54],"(RDS)":[55],"method":[56,157],"learn":[58],"how":[59],"sample":[61],"adequately":[63],"search":[66],"useful":[68,174],"models":[69],"insights.":[71],"We":[72,127],"formulate":[73],"optimisation":[75],"problem":[76],"model":[78,93,171],"diversification":[79,172],"$\u03b4{-div}$":[80],"in":[81],"sampling":[83,142,160,169],"maximise":[85],"potentials":[87,185],"optimum":[89],"allocation":[90],"by":[91],"injecting":[92],"diversity.":[94],"work":[96],"advocates":[97],"employment":[99],"diverse":[101],"base":[102],"learners":[103],"as":[104,108,192],"value":[105],"functions":[106],"such":[107,191],"neural":[109],"networks,":[110],"decision":[111],"trees,":[112],"or":[113,179],"logistic":[114],"regressions":[115],"reinforce":[117],"subsets":[123],"with":[124],"multi-modal":[125],"belief.":[126],"introduce":[128],"different":[129],"ensemble":[130],"reward":[131],"mechanisms,":[132],"including":[133],"soft":[134],"voting":[135],"stochastic":[137],"choice":[138],"approximate":[140],"optimal":[141],"policy.":[143],"The":[144,196],"evaluation":[145],"conducted":[146],"four":[148],"datasets":[149],"evidently":[150],"highlights":[151],"benefits":[153],"using":[155],"RDS":[156],"over":[158],"traditional":[159],"approaches.":[161],"Our":[162],"experimental":[163],"results":[164],"suggest":[165],"that":[166],"trainable":[168],"is":[173,199],"competition":[176],"organisers,":[177],"researchers,":[178],"even":[180],"starters":[181],"pursue":[183],"full":[184],"tasks":[190],"classification":[193],"regression.":[195],"source":[197],"code":[198],"available":[200],"at":[201],"https://github.com/probeu/RDS.":[202]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-09-21T07:43:02.447757","created_date":"2025-10-10T00:00:00"}