{"id":"https://openalex.org/W3127098609","doi":"https://doi.org/10.48550/arxiv.2102.02400","title":"Provably End-to-end Label-Noise Learning without Anchor Points","display_name":"Provably End-to-end Label-Noise Learning without Anchor Points","alternate_titles":[],"publication_year":2021,"publication_date":"2021-02-04","ids":{"openalex":"https://openalex.org/W3127098609","doi":"https://doi.org/10.48550/arxiv.2102.02400","mag":"3127098609"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2102.02400","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.02400","pdf_url":"https://arxiv.org/pdf/2102.02400","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"},"parent_works":[],"lineage":["https://openalex.org/W3127098609"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.02400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100400533","display_name":"Xuefeng Li","orcid":"https://orcid.org/0000-0001-9671-2616","observed_orcids":["https://orcid.org/0000-0001-9671-2616"]},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Li, Xuefeng","raw_affiliation_strings":["University of New South Wales,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,#TAB#","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065250332","display_name":"Tongliang Liu","orcid":"https://orcid.org/0000-0002-9640-6472","observed_orcids":["https://orcid.org/0000-0002-9640-6472"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liu, Tongliang","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047240103","display_name":"Bo Han","orcid":"https://orcid.org/0000-0002-6338-0958","observed_orcids":["https://orcid.org/0000-0002-6338-0958"]},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]},{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["HK","JP"],"is_corresponding":false,"raw_author_name":"Han, Bo","raw_affiliation_strings":["HKBU / RIKEN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKBU / RIKEN","institution_ids":["https://openalex.org/I141568987","https://openalex.org/I4210110652"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Niu, Gang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Niu, Gang","raw_affiliation_strings":["RIKEN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN","institution_ids":["https://openalex.org/I4210110652"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743","observed_orcids":["https://orcid.org/0000-0001-6658-6743"]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sugiyama, Masashi","raw_affiliation_strings":["RIKEN / The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN / The University of Tokyo","institution_ids":["https://openalex.org/I4210110652","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":138,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","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"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":9.999999747378752e-05,"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/noisy-labels","display_name":"label noise","score":0.7620000243186951},{"id":"https://openalex.org/keywords/transition-matrix-estimation","display_name":"transition matrix estimation","score":0.8399999737739563},{"id":"https://openalex.org/keywords/anchor-points","display_name":"anchor points","score":0.8510000109672546},{"id":"https://openalex.org/keywords/statistical-consistency","display_name":"statistical consistency","score":0.6700000166893005},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.7559999823570251},{"id":"https://openalex.org/keywords/simplex-volume","display_name":"simplex volume","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6542277336120605},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6451293230056763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6238350868225098},{"id":"https://openalex.org/C49555168","wikidata":"https://www.wikidata.org/wiki/Q176583","display_name":"Stochastic matrix","level":3,"score":0.587736964225769},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5663973093032837},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5129613280296326},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47402575612068176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4724850058555603},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46654701232910156},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4366075098514557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37543898820877075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3286495804786682},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25720149278640747},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1189015805721283},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.09492212533950806},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2102.02400","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.02400","pdf_url":"https://arxiv.org/pdf/2102.02400","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.2102.02400","doi":"https://doi.org/10.48550/arxiv.2102.02400","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.02400","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:2102.02400","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.02400","pdf_url":"https://arxiv.org/pdf/2102.02400","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":[{"id":"https://openalex.org/G2189095408","display_name":null,"funder_award_id":"62006202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320320955","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131"},{"id":"https://openalex.org/F4320320966","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3127098609.pdf","grobid_xml":"https://content.openalex.org/works/W3127098609.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W100063776","https://openalex.org/W1514928307","https://openalex.org/W1866072925","https://openalex.org/W1916337001","https://openalex.org/W1921293667","https://openalex.org/W1997201895","https://openalex.org/W2101837437","https://openalex.org/W2113290770","https://openalex.org/W2121056381","https://openalex.org/W2129062845","https://openalex.org/W2156458885","https://openalex.org/W2296319761","https://openalex.org/W2513096609","https://openalex.org/W2610265803","https://openalex.org/W2611425310","https://openalex.org/W2682189153","https://openalex.org/W2743200750","https://openalex.org/W2752365628","https://openalex.org/W2752971446","https://openalex.org/W2795282075","https://openalex.org/W2798766386","https://openalex.org/W2799090584","https://openalex.org/W2804077623","https://openalex.org/W2804378530","https://openalex.org/W2909793444","https://openalex.org/W2947049994","https://openalex.org/W2950220847","https://openalex.org/W2962682420","https://openalex.org/W2963081269","https://openalex.org/W2963735582","https://openalex.org/W2963759070","https://openalex.org/W2963909971","https://openalex.org/W2964234160","https://openalex.org/W2964274690","https://openalex.org/W2964292098","https://openalex.org/W2970038028","https://openalex.org/W2970956502","https://openalex.org/W2978471258","https://openalex.org/W2996108195","https://openalex.org/W2998301463","https://openalex.org/W3034954777","https://openalex.org/W3035314656","https://openalex.org/W3035370681","https://openalex.org/W3035412368","https://openalex.org/W3035753488","https://openalex.org/W3092841986","https://openalex.org/W3102643535","https://openalex.org/W3103846556","https://openalex.org/W3104255659","https://openalex.org/W3123795136","https://openalex.org/W3129100675","https://openalex.org/W3168889651","https://openalex.org/W3170414933","https://openalex.org/W3171240668","https://openalex.org/W6982974507"],"related_works":["https://openalex.org/W2947049994","https://openalex.org/W3129100675","https://openalex.org/W7169798508","https://openalex.org/W3165676168","https://openalex.org/W3034950264","https://openalex.org/W3102643535","https://openalex.org/W7215062549","https://openalex.org/W3126748415","https://openalex.org/W7000858924","https://openalex.org/W4320812386"],"abstract_inverted_index":{"In":[0,40],"label-noise":[1,50],"learning,":[2],"the":[3,19,30,62,67,71,75,79,82,86,89,97,101,112,117,124,136,141],"transition":[4,20,90,98,118],"matrix":[5,21,99,119],"plays":[6],"a":[7],"key":[8],"role":[9],"in":[10,37,55],"building":[11],"statistically":[12,128],"consistent":[13,16],"classifiers.":[14],"Existing":[15],"estimators":[17],"for":[18,48],"have":[22],"been":[23],"developed":[24],"by":[25,74,85,110],"exploiting":[26],"anchor":[27,53],"points.":[28],"However,":[29],"anchor-point":[31],"assumption":[32,114],"is":[33,109,120,127],"not":[34],"always":[35],"satisfied":[36],"real":[38],"scenarios.":[39],"this":[41],"paper,":[42],"we":[43,57],"propose":[44],"an":[45],"end-to-end":[46],"framework":[47,94],"solving":[49],"learning":[51],"without":[52],"points,":[54],"which":[56,116],"simultaneously":[58],"optimize":[59],"two":[60],"objectives:":[61],"cross":[63],"entropy":[64],"loss":[65],"between":[66],"noisy":[68],"label":[69],"and":[70,78,123,138],"predicted":[72],"probability":[73],"neural":[76],"network,":[77],"volume":[80],"of":[81,88,140],"simplex":[83],"formed":[84],"columns":[87],"matrix.":[91],"Our":[92],"proposed":[93,142],"can":[95],"identify":[96],"if":[100],"clean":[102],"class-posterior":[103],"probabilities":[104],"are":[105],"sufficiently":[106],"scattered.":[107],"This":[108],"far":[111],"mildest":[113],"under":[115],"provably":[121],"identifiable":[122],"learned":[125],"classifier":[126],"consistent.":[129],"Experimental":[130],"results":[131],"on":[132],"benchmark":[133],"datasets":[134],"demonstrate":[135],"effectiveness":[137],"robustness":[139],"method.":[143]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3127098609","counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-17T12:49:18.490984","created_date":"2021-02-15T00:00:00"}
