{"id":"https://openalex.org/W7212259177","doi":"https://doi.org/10.48550/arxiv.2609.10928","title":"AUC Maximization from Biased Positive-unlabeled Data with Confidence","display_name":"AUC Maximization from Biased Positive-unlabeled Data with Confidence","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7212259177","doi":"https://doi.org/10.48550/arxiv.2609.10928"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.10928","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.10928","pdf_url":"https://arxiv.org/pdf/2609.10928","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/2609.10928","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030880294","display_name":"Atsutoshi Kumagai","orcid":"https://orcid.org/0000-0002-2915-4615","observed_orcids":["https://orcid.org/0000-0002-2915-4615"]},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kumagai, Atsutoshi","raw_affiliation_strings":["NTT, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT, Inc","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034538103","display_name":"Tomoharu Iwata","orcid":"https://orcid.org/0000-0003-4425-1971","observed_orcids":["https://orcid.org/0000-0003-4425-1971"]},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Iwata, Tomoharu","raw_affiliation_strings":["NTT, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT, Inc","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151365867","display_name":"Hiroshi Takahashi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahashi, Hiroshi","raw_affiliation_strings":["NTT, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT, Inc","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084250200","display_name":"Taishi Nishiyama","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nishiyama, Taishi","raw_affiliation_strings":["NTT, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT, Inc","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040969124","display_name":"Kazuki Adachi","orcid":"https://orcid.org/0009-0003-3131-8732","observed_orcids":["https://orcid.org/0009-0003-3131-8732"]},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Adachi, Kazuki","raw_affiliation_strings":["NTT, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT, Inc","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5149554723","display_name":"Yasuhiro Fujiwara","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fujiwara, Yasuhiro","raw_affiliation_strings":["NTT, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT, Inc","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.5464000105857849,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.5464000105857849,"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":0.4406999945640564,"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":0.0005000000237487257,"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/auc-maximization","display_name":"AUC maximization","score":0.9879999756813049},{"id":"https://openalex.org/keywords/positive-unlabeled-learning","display_name":"positive-unlabeled learning","score":0.8809999823570251},{"id":"https://openalex.org/keywords/confidence-estimation","display_name":"confidence estimation","score":0.7360000014305115},{"id":"https://openalex.org/keywords/imbalanced-binary-classification","display_name":"imbalanced binary classification","score":0.9190000295639038},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"posterior probability","score":0.6309999823570251}],"concepts":[{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6904000043869019},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.666100025177002},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4948999881744385},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4553999900817871},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3939000070095062},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.3910999894142151},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3871000111103058},{"id":"https://openalex.org/C2779190172","wikidata":"https://www.wikidata.org/wiki/Q4913888","display_name":"Binary data","level":3,"score":0.37040001153945923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3675999939441681},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26600000262260437}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.10928","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.10928","pdf_url":"https://arxiv.org/pdf/2609.10928","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.2609.10928","doi":"https://doi.org/10.48550/arxiv.2609.10928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.10928","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.10928","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.10928","pdf_url":"https://arxiv.org/pdf/2609.10928","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212259177.pdf","grobid_xml":"https://content.openalex.org/works/W7212259177.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7216392358","https://openalex.org/W2611891615","https://openalex.org/W7204816811","https://openalex.org/W4283807219","https://openalex.org/W3018512573","https://openalex.org/W3006921515","https://openalex.org/W4321021439","https://openalex.org/W7168814307","https://openalex.org/W3190417026","https://openalex.org/W2273684912"],"abstract_inverted_index":{"Maximizing":[0],"the":[1,4,27,45,77,99,107,118,127,139,158,169,178,185],"area":[2],"under":[3,151],"receiver":[5],"operating":[6],"characteristic":[7],"curve":[8],"(AUC)":[9],"is":[10,85,112,123,172],"a":[11,95,163],"standard":[12],"approach":[13],"to":[14,34,41,50,97,113],"imbalanced":[15],"binary":[16],"classification.":[17],"Although":[18],"positive":[19,57,71,79,132],"and":[20,58],"negative":[21,29],"data":[22,30,61,72,145],"are":[23,31,73],"required":[24],"for":[25,47],"maximizing":[26],"AUC,":[28],"often":[32,86],"difficult":[33],"collect":[35],"in":[36,88],"some":[37],"real-world":[38,192],"applications":[39],"due":[40],"privacy":[42],"concerns":[43],"or":[44],"need":[46],"specialized":[48],"expertise":[49],"annotate":[51],"them.":[52],"Thus,":[53],"AUC":[54,100,140,149,160,165],"maximization":[55,150],"from":[56,76,101],"unlabeled":[59],"(PU)":[60],"has":[62],"been":[63],"attracting":[64],"attention.":[65],"Existing":[66],"methods":[67],"assume":[68],"that":[69,120,157],"labeled":[70,131],"unbiased":[74],"samples":[75],"true":[78,179],"distribution.":[80],"However,":[81],"this":[82,91],"ideal":[83],"assumption":[84],"violated":[87],"practice.":[89],"In":[90],"paper,":[92],"we":[93],"propose":[94],"method":[96,189],"maximize":[98],"biased":[102,143],"PU":[103,144],"data.":[104,133],"To":[105],"address":[106],"bias,":[108],"our":[109,188],"key":[110],"idea":[111],"exploit":[114],"{\\it":[115],"confidence},":[116],"i.e.,":[117],"probability":[119],"an":[121,136],"instance":[122],"positive,":[124],"associated":[125],"with":[126,146],"small":[128],"number":[129],"of":[130,138,177,187],"We":[134,154,182],"derive":[135],"estimator":[137],"risk":[141,161],"using":[142],"confidence,":[147],"enabling":[148],"such":[152],"bias.":[153],"further":[155],"show":[156,184],"rewritten":[159],"induces":[162],"Bayes-optimal":[164],"ranking":[166],"even":[167],"when":[168],"available":[170],"confidence":[171],"any":[173],"strictly":[174],"increasing":[175],"transformation":[176],"posterior":[180],"probability.":[181],"experimentally":[183],"effectiveness":[186],"on":[190],"eight":[191],"datasets.":[193]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-12T00:00:00"}