{"id":"https://openalex.org/W3042158453","doi":"https://doi.org/10.1145/3492324.3494166","title":"TrustNet: Learning from Trusted Data Against (A)symmetric Label Noise","display_name":"TrustNet: Learning from Trusted Data Against (A)symmetric Label Noise","publication_year":2021,"publication_date":"2021-12-06","ids":{"openalex":"https://openalex.org/W3042158453","doi":"https://doi.org/10.1145/3492324.3494166","mag":"3042158453"},"language":"en","primary_location":{"id":"doi:10.1145/3492324.3494166","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3492324.3494166","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3492324.3494166","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM 8th International Conference on Big Data Computing, Applications and Technologies (BDCAT '21)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3492324.3494166","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029394537","display_name":"Amirmasoud Ghiassi","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Amirmasoud Ghiassi","raw_affiliation_strings":["Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000838509","display_name":"Robert Birke","orcid":"https://orcid.org/0000-0003-1144-3707"},"institutions":[{"id":"https://openalex.org/I885143765","display_name":"ABB (Switzerland)","ror":"https://ror.org/00ks5vt51","country_code":"CH","type":"company","lineage":["https://openalex.org/I885143765"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Robert Birke","raw_affiliation_strings":["ABB Research, Switzerland"],"affiliations":[{"raw_affiliation_string":"ABB Research, Switzerland","institution_ids":["https://openalex.org/I885143765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013859152","display_name":"Lydia Y. Chen","orcid":"https://orcid.org/0000-0002-4228-6735"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lydia Y.Chen","raw_affiliation_strings":["Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029394537"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.1398,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51067607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.9940999746322632,"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/robustness","display_name":"Robustness (evolution)","score":0.8510924577713013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7682784795761108},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6499534249305725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5953094363212585},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.526006817817688},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5208193063735962},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5088325142860413},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4882631301879883},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4667549133300781},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4275388717651367},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4008732736110687},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38104185461997986},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20078209042549133}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8510924577713013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682784795761108},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6499534249305725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5953094363212585},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.526006817817688},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5208193063735962},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5088325142860413},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4882631301879883},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4667549133300781},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4275388717651367},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4008732736110687},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38104185461997986},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20078209042549133},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3492324.3494166","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3492324.3494166","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3492324.3494166","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM 8th International Conference on Big Data Computing, Applications and Technologies (BDCAT '21)","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:23f38d97-b491-4b66-9830-6f0773e243c9","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:23f38d97-b491-4b66-9830-6f0773e243c9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.1145/3492324.3494166","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3492324.3494166","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3492324.3494166","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM 8th International Conference on Big Data Computing, Applications and Technologies (BDCAT '21)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1025993280","display_name":null,"funder_award_id":"NRP75 project 407540_167266","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G5803154810","display_name":null,"funder_award_id":"407540_167266","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G8311046018","display_name":null,"funder_award_id":"167266","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G879380985","display_name":"Topology of intracellular synthesis and plasma membrane dis- tribution of glycoconjugates","funder_award_id":"40754","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3042158453.pdf","grobid_xml":"https://content.openalex.org/works/W3042158453.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1866072925","https://openalex.org/W1921293667","https://openalex.org/W1972675781","https://openalex.org/W2065151783","https://openalex.org/W2117539524","https://openalex.org/W2167460663","https://openalex.org/W2622100130","https://openalex.org/W2752971446","https://openalex.org/W2909793444","https://openalex.org/W2911736639","https://openalex.org/W2943997064","https://openalex.org/W2962682420","https://openalex.org/W2962762068","https://openalex.org/W2962762541","https://openalex.org/W2962974744","https://openalex.org/W2963081269","https://openalex.org/W2963096987","https://openalex.org/W2963207607","https://openalex.org/W2963644303","https://openalex.org/W2963735582","https://openalex.org/W2963759070","https://openalex.org/W2963789034","https://openalex.org/W2964096266","https://openalex.org/W2964155802","https://openalex.org/W2964234160","https://openalex.org/W2964292098","https://openalex.org/W2964309657","https://openalex.org/W2967052791","https://openalex.org/W2969215546","https://openalex.org/W2981873476","https://openalex.org/W2990019157","https://openalex.org/W3009445099","https://openalex.org/W3042065397","https://openalex.org/W3137695714","https://openalex.org/W3156669901","https://openalex.org/W6738471490"],"related_works":["https://openalex.org/W3000197790","https://openalex.org/W4312659495","https://openalex.org/W4385366257","https://openalex.org/W3101007570","https://openalex.org/W4387910575","https://openalex.org/W3176425421","https://openalex.org/W3091312527","https://openalex.org/W1555087354","https://openalex.org/W4287865546","https://openalex.org/W3007306981"],"abstract_inverted_index":{"Big":[0],"Data":[1],"systems":[2],"allow":[3],"collecting":[4],"massive":[5],"datasets":[6,17],"to":[7,32,49],"feed":[8],"the":[9,80,93,101,130,134,138,178],"data":[10,166],"hungry":[11],"deep":[12,46],"learning.":[13],"Labelling":[14],"these":[15],"ever-bigger":[16],"is":[18,121,144],"increasingly":[19],"challenging":[20],"and":[21,59,163],"label":[22,33,158,168],"errors":[23],"affect":[24],"even":[25],"highly":[26],"curated":[27],"sets.":[28],"This":[29],"makes":[30],"robustness":[31,67,180],"noise":[34,57,72,89,104,140,159,188],"a":[35,52,113,124,184],"critical":[36],"property":[37],"for":[38,86,160],"weakly-supervised":[39],"classifiers.":[40],"The":[41,142],"related":[42],"works":[43],"on":[44,51,63,92,147,156],"resilient":[45],"networks":[47],"tend":[48],"focus":[50],"limited":[53],"set":[54,115,186],"of":[55,83,103,116,181,187],"synthetic":[56,157],"patterns,":[58],"with":[60,167],"disparate":[61],"views":[62],"their":[64],"impacts,":[65],"e.g.,":[66],"against":[68,133,174],"symmetric":[69,109],"v.s.":[70],"asymmetric":[71],"patterns.":[73,90,189],"In":[74],"this":[75],"paper,":[76],"we":[77,95],"first":[78,99],"extend":[79],"theoretical":[81],"analysis":[82],"test":[84],"accuracy":[85],"any":[87],"given":[88,131],"Based":[91],"insights,":[94],"design":[96],"TrustNet":[97,120,155,182],"that":[98],"learns":[100],"pattern":[102],"corruption,":[105],"being":[106],"it":[107],"both":[108],"or":[110],"asymmetric,":[111],"from":[112,137],"small":[114],"trusted":[117],"data.":[118],"Then,":[119],"trained":[122],"via":[123],"robust":[125],"loss":[126],"function,":[127],"which":[128],"weights":[129],"labels":[132,136],"inferred":[135],"learned":[139],"pattern.":[141],"weight":[143],"adjusted":[145],"based":[146],"model":[148],"uncertainty":[149],"across":[150],"training":[151],"epochs.":[152],"We":[153,172],"evaluate":[154],"CIFAR-10,":[161],"CIFAR-100":[162],"big":[164],"real-world":[165],"noise,":[169],"i.e.,":[170],"Clothing1M.":[171],"compare":[173],"state-of-the-art":[175],"methods":[176],"demonstrating":[177],"strong":[179],"under":[183],"diverse":[185]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}