{"id":"https://openalex.org/W3201164804","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533798","title":"Training Classifiers that are Universally Robust to All Label Noise Levels","display_name":"Training Classifiers that are Universally Robust to All Label Noise Levels","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3201164804","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533798","mag":"3201164804"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100610905","display_name":"Jingyi Xu","orcid":"https://orcid.org/0000-0001-7608-2354"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Jingyi Xu","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030858163","display_name":"Tony Q. S. Quek","orcid":"https://orcid.org/0000-0002-4037-3149"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tony Q. S. Quek","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076984139","display_name":"Kai Fong Ernest Chong","orcid":"https://orcid.org/0000-0001-5568-7610"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kai Fong Ernest Chong","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100610905"],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69012106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9833999872207642,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9700000286102295,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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","display_name":"Training (meteorology)","score":0.6795642375946045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.655940592288971},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5810458660125732},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5790331363677979},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5638217329978943},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4628561735153198},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4365549683570862}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6795642375946045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.655940592288971},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5810458660125732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5790331363677979},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5638217329978943},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4628561735153198},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4365549683570862},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G54285798","display_name":null,"funder_award_id":"AISG-RP-2019-015","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1593505700","https://openalex.org/W1821462560","https://openalex.org/W1861993554","https://openalex.org/W1866072925","https://openalex.org/W1921293667","https://openalex.org/W2050871273","https://openalex.org/W2121056381","https://openalex.org/W2123958887","https://openalex.org/W2132442585","https://openalex.org/W2302255633","https://openalex.org/W2592335154","https://openalex.org/W2620673134","https://openalex.org/W2765407302","https://openalex.org/W2793406320","https://openalex.org/W2803187616","https://openalex.org/W2809237945","https://openalex.org/W2885593519","https://openalex.org/W2891244534","https://openalex.org/W2912934387","https://openalex.org/W2941387380","https://openalex.org/W2947380870","https://openalex.org/W2948447329","https://openalex.org/W2948606739","https://openalex.org/W2952361104","https://openalex.org/W2962762068","https://openalex.org/W2962762541","https://openalex.org/W2963081269","https://openalex.org/W2963460857","https://openalex.org/W2963659419","https://openalex.org/W2963697299","https://openalex.org/W2963735582","https://openalex.org/W2963759070","https://openalex.org/W2964096266","https://openalex.org/W2964273174","https://openalex.org/W2964274690","https://openalex.org/W2964292098","https://openalex.org/W2964309657","https://openalex.org/W2967052791","https://openalex.org/W2970038028","https://openalex.org/W2978625989","https://openalex.org/W2981873476","https://openalex.org/W2990019157","https://openalex.org/W2996108195","https://openalex.org/W3034185248","https://openalex.org/W3035429562","https://openalex.org/W3035546924","https://openalex.org/W3037062548","https://openalex.org/W3092841986","https://openalex.org/W3118608800","https://openalex.org/W3137695714","https://openalex.org/W4212883601","https://openalex.org/W6638523607","https://openalex.org/W6639315830","https://openalex.org/W6639331287","https://openalex.org/W6640298173","https://openalex.org/W6698183232","https://openalex.org/W6738763127","https://openalex.org/W6745136726","https://openalex.org/W6747898760","https://openalex.org/W6751420435","https://openalex.org/W6753772092","https://openalex.org/W6762161020","https://openalex.org/W6763430915","https://openalex.org/W6763485134","https://openalex.org/W6766952621","https://openalex.org/W6771630921","https://openalex.org/W6779784029","https://openalex.org/W6783943466","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"For":[0],"classification":[1],"tasks,":[2],"deep":[3],"neural":[4],"networks":[5],"are":[6,19,54,63],"prone":[7],"to":[8,21,57,66,102,209],"overfitting":[9],"in":[10,69,229],"the":[11,45,70,112,124,162,165,175,182],"presence":[12],"of":[13,83,95,123,164],"label":[14,46,187],"noise.":[15,198],"Although":[16],"existing":[17,232],"methods":[18],"able":[20],"alleviate":[22],"this":[23,156],"problem":[24],"at":[25,34,40,189,207],"low":[26],"noise":[27,36,42,47,59,71,188,191,211],"levels,":[28,37,60],"they":[29],"encounter":[30],"significant":[31],"performance":[32],"reduction":[33],"high":[35,210],"or":[38],"even":[39],"medium":[41,208],"levels":[43,192],"when":[44],"is":[48,100,116],"asymmetric.":[49],"To":[50],"train":[51,151,170],"classifiers":[52],"that":[53,62,78,91,202],"universally":[55],"robust":[56],"all":[58],"and":[61,196,224],"not":[64],"sensitive":[65],"any":[67,96],"variation":[68],"model,":[72,167],"we":[73,88,107,168,225],"propose":[74],"a":[75,80,92,152,171,220],"distillation-based":[76],"framework":[77,121,204,217],"incorporates":[79],"new":[81],"subcategory":[82],"Positive-Unlabeled":[84],"learning.":[85],"In":[86],"particular,":[87],"shall":[89,130,150],"assume":[90],"small":[93],"subset":[94,115,138],"given":[97],"noisy":[98,114,222],"dataset":[99,184],"known":[101],"have":[103],"correct":[104],"labels,":[105],"which":[106],"treat":[108],"as":[109,118],"\u201cpositive\u201d,":[110],"while":[111],"remaining":[113],"treated":[117],"\u201cunlabeled\u201d.":[119],"Our":[120],"consists":[122],"following":[125],"two":[126],"components:":[127],"(1)":[128],"We":[129,149,213],"generate,":[131],"via":[132],"iterative":[133],"updates,":[134],"an":[135],"augmented":[136,158],"clean":[137,159],"with":[139,185],"additional":[140],"reliable":[141],"\u201cpositive\u201d":[142],"samples":[143],"filtered":[144],"from":[145],"\u201cunlabeled\u201d":[146],"samples;":[147],"(2)":[148],"teacher":[153,166],"model":[154,173],"on":[155,174,181,218],"larger":[157],"set.":[160],"With":[161],"guidance":[163],"then":[169],"student":[172],"whole":[176],"dataset.":[177],"Experiments":[178],"were":[179],"conducted":[180],"CIFAR-10":[183],"synthetic":[186],"multiple":[190],"for":[193],"both":[194],"symmetric":[195],"asymmetric":[197],"The":[199],"results":[200],"show":[201],"our":[203,216],"generally":[205],"outperforms":[206],"levels.":[212],"also":[214],"evaluated":[215],"Clothing1M,":[219],"real-world":[221],"dataset,":[223],"achieved":[226],"2.94%":[227],"improvement":[228],"accuracy":[230],"over":[231],"state-of-the-art":[233],"methods.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}