{"id":"https://openalex.org/W7138139191","doi":"https://doi.org/10.48550/arxiv.2603.13894","title":"Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels","display_name":"Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138139191","doi":"https://doi.org/10.48550/arxiv.2603.13894"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.13894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.13894","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003070543","display_name":"Zikai Lin","orcid":"https://orcid.org/0000-0002-0300-9452"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lin, Zhanhui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129662029","display_name":"Yanlin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yanlin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113827261","display_name":"Sanping Zhou","orcid":"https://orcid.org/0000-0003-4100-2304"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Sanping","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003070543"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9890999794006348,"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":0.9890999794006348,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.001500000013038516,"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/T10057","display_name":"Face and Expression Recognition","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6333000063896179},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5605000257492065},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5569000244140625},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5396999716758728},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5315999984741211},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4903999865055084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4507000148296356},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4415000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6909999847412109},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6333000063896179},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5605000257492065},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5315999984741211},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47749999165534973},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C202286095","wikidata":"https://www.wikidata.org/wiki/Q579262","display_name":"Error function","level":2,"score":0.2718000113964081}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.13894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.13894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.42713749408721924}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Training":[0],"deep":[1],"neural":[2,66],"networks":[3],"with":[4,118],"noisy":[5,41,78,129],"labels":[6],"remains":[7],"a":[8,53,63,71,89],"significant":[9],"challenge,":[10],"often":[11,35],"leading":[12],"to":[13,84],"degraded":[14],"performance.":[15],"Existing":[16],"methods":[17],"for":[18,126],"handling":[19],"label":[20,55],"noise":[21,28],"typically":[22],"rely":[23],"on":[24,108],"either":[25],"transition":[26],"matrix,":[27],"detection,":[29],"or":[30],"meta-learning":[31],"techniques,":[32],"but":[33],"they":[34],"exhibit":[36],"low":[37],"utilization":[38],"efficiency":[39],"of":[40,102],"samples":[42],"and":[43,65,81,105,113],"incur":[44],"high":[45],"computational":[46],"costs.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"self-training":[54],"correction":[56,67],"framework":[57],"using":[58],"decoupled":[59],"bilevel":[60],"optimization,":[61],"where":[62],"classifier":[64],"function":[68],"co-evolve.":[69],"Leveraging":[70],"small":[72],"clean":[73],"dataset,":[74],"our":[75,103],"method":[76],"employs":[77],"posterior":[79],"simulation":[80],"intermediate":[82],"features":[83],"transfer":[85],"ground-truth":[86],"knowledge,":[87],"forming":[88],"closed-loop":[90],"feedback":[91],"system":[92],"that":[93],"prevents":[94],"error":[95],"amplification.":[96],"Theoretical":[97],"guarantees":[98],"underpin":[99],"the":[100],"stability":[101],"approach,":[104],"extensive":[106],"experiments":[107],"benchmark":[109],"datasets":[110],"like":[111],"CIFAR":[112],"Clothing1M":[114],"confirm":[115],"state-of-the-art":[116],"performance":[117],"reduced":[119],"training":[120],"time,":[121],"highlighting":[122],"its":[123],"practical":[124],"applicability":[125],"learning":[127],"from":[128],"labels.":[130]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}