{"id":"https://openalex.org/W4414581705","doi":"https://doi.org/10.1007/s10994-025-06860-8","title":"Learning with confidence: training better classifiers from soft labels","display_name":"Learning with confidence: training better classifiers from soft labels","publication_year":2025,"publication_date":"2025-09-28","ids":{"openalex":"https://openalex.org/W4414581705","doi":"https://doi.org/10.1007/s10994-025-06860-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-025-06860-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06860-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06860-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06860-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073500893","display_name":"Sjoerd de Vries","orcid":"https://orcid.org/0000-0002-5306-6797"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]},{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]},{"id":"https://openalex.org/I3018483916","display_name":"University Medical Center Utrecht","ror":"https://ror.org/0575yy874","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I3018483916"]}],"countries":["DE","NL"],"is_corresponding":true,"raw_author_name":"Sjoerd de Vries","raw_affiliation_strings":["Department of Digital Health, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands","Department of Information and Computing Sciences, Utrecht University, Princetonplein 5, 3584 CC, Utrecht, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Digital Health, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353","https://openalex.org/I3018483916","https://openalex.org/I223822909","https://openalex.org/I2802164966"]},{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Princetonplein 5, 3584 CC, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063460579","display_name":"Dirk Thierens","orcid":"https://orcid.org/0000-0002-9308-5159"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dirk Thierens","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Princetonplein 5, 3584 CC, Utrecht, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Princetonplein 5, 3584 CC, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073500893"],"corresponding_institution_ids":["https://openalex.org/I193662353","https://openalex.org/I223822909","https://openalex.org/I2802164966","https://openalex.org/I3018483916"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":5.1907,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95661801,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"114","issue":"11","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":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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":0.9972000122070312,"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/training-set","display_name":"Training set","score":0.4936000108718872},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4625000059604645},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42890000343322754},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.3659999966621399},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.3544999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373999953269958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7192000150680542},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6644999980926514},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42890000343322754},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3402000069618225},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C140073362","wikidata":"https://www.wikidata.org/wiki/Q738759","display_name":"Soft computing","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-025-06860-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06860-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06860-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-025-06860-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06860-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06860-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414581705.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1517796226","https://openalex.org/W1603071803","https://openalex.org/W1826524928","https://openalex.org/W1963596489","https://openalex.org/W1979903243","https://openalex.org/W2034841618","https://openalex.org/W2038790645","https://openalex.org/W2083265890","https://openalex.org/W2091825929","https://openalex.org/W2103459159","https://openalex.org/W2113023411","https://openalex.org/W2125943921","https://openalex.org/W2128314196","https://openalex.org/W2142261479","https://openalex.org/W2164646550","https://openalex.org/W2165466912","https://openalex.org/W2167055186","https://openalex.org/W2167460663","https://openalex.org/W2186046013","https://openalex.org/W2285559238","https://openalex.org/W2330485005","https://openalex.org/W2475282416","https://openalex.org/W2553156677","https://openalex.org/W2790660115","https://openalex.org/W2875415200","https://openalex.org/W2906329876","https://openalex.org/W2912934387","https://openalex.org/W3005295611","https://openalex.org/W3105616927","https://openalex.org/W3119385233","https://openalex.org/W3166716308","https://openalex.org/W4224995877","https://openalex.org/W4236654676","https://openalex.org/W4280626955","https://openalex.org/W4292157289","https://openalex.org/W4410369930"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"In":[1],"supervised":[2],"machine":[3],"learning,":[4],"models":[5],"are":[6,144,172,210],"typically":[7],"trained":[8],"using":[9,114],"data":[10,121,136],"with":[11,122,203],"hard":[12,110,131,186,221],"labels,":[13,53,124],"i.e.,":[14],"definite":[15],"assignments":[16],"of":[17,63,76,102,169,192],"class":[18,52],"membership.":[19],"This":[20],"traditional":[21,215],"approach,":[22],"however,":[23],"does":[24],"not":[25],"take":[26],"the":[27,51,60,73,100,125,130,150,185,190,197,207,214,219],"inherent":[28],"uncertainty":[29],"in":[30,85,189],"these":[31],"labels":[32,113,143,222],"into":[33],"account.":[34],"We":[35,70],"investigate":[36],"whether":[37],"incorporating":[38],"label":[39,78,132,187],"uncertainty,":[40],"represented":[41],"for":[42,81,90,106,217],"each":[43],"instance":[44],"as":[45,55],"a":[46,56,86,200],"discrete":[47],"probability":[48,154],"distribution":[49],"over":[50],"known":[54,173],"soft":[57,77,112,142],"label,":[58],"improves":[59],"predictive":[61],"performance":[62,101],"classification":[64],"models,":[65,163],"focusing":[66],"on":[67,157,199],"tabular":[68],"data.":[69,96],"first":[71],"demonstrate":[72],"potential":[74],"value":[75],"learning":[79,107],"(SLL)":[80],"estimating":[82],"model":[83,158],"parameters":[84],"simulation":[87],"experiment,":[88],"particularly":[89],"limited":[91],"sample":[92],"sizes":[93],"and":[94,111,140],"imbalanced":[95],"Subsequently,":[97],"we":[98,148,195],"compare":[99],"various":[103],"wrapper":[104],"methods":[105,127,183,188,198,209,216],"from":[108],"both":[109],"identical":[115],"base":[116],"classifiers.":[117],"On":[118],"real-world-inspired":[119],"synthetic":[120],"clean":[123],"SLL":[126,182,208],"consistently":[128],"outperform":[129,184],"methods.":[133],"Since":[134],"real-world":[135,201],"is":[137],"often":[138],"noisy":[139,153],"precise":[141],"challenging":[145],"to":[146,174,212],"obtain,":[147],"study":[149,165],"effect":[151],"that":[152,171,181],"estimates":[155],"have":[156],"performance.":[159],"Alongside":[160],"conventional":[161],"noise":[162],"our":[164],"examines":[166],"four":[167],"types":[168],"miscalibration":[170],"affect":[175],"human":[176],"annotators.":[177],"The":[178],"results":[179],"show":[180],"majority":[191],"settings.":[193],"Finally,":[194],"evaluate":[196],"dataset":[202],"confidence":[204,227],"scores,":[205],"where":[206],"shown":[211],"match":[213],"predicting":[218],"(noisy)":[220],"while":[223],"providing":[224],"more":[225],"accurate":[226],"estimates.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}