{"id":"https://openalex.org/W4389982907","doi":"https://doi.org/10.48550/arxiv.2312.10324","title":"Federated Learning with Instance-Dependent Noisy Label","display_name":"Federated Learning with Instance-Dependent Noisy Label","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4389982907","doi":"https://doi.org/10.48550/arxiv.2312.10324"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.10324","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.10324","pdf_url":"https://arxiv.org/pdf/2312.10324","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.10324","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100436173","display_name":"Lei Wang","orcid":"https://orcid.org/0009-0003-1939-5532"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Lei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012540094","display_name":"Jieming Bian","orcid":"https://orcid.org/0000-0002-6372-6357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bian, Jieming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101228095","display_name":"Jie Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jie","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100436173"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":0.977400004863739,"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":0.977400004863739,"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":0.9610000252723694,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9319999814033508,"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/computer-science","display_name":"Computer science","score":0.8190198540687561},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6657052040100098},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6180258393287659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5824337601661682},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5648531913757324},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5009076595306396},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4430440366268158},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.418254554271698},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40196219086647034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190198540687561},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6657052040100098},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6180258393287659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5824337601661682},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5648531913757324},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5009076595306396},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4430440366268158},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.418254554271698},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40196219086647034},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.10324","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.10324","pdf_url":"https://arxiv.org/pdf/2312.10324","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.10324","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.10324","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.10324","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.10324","pdf_url":"https://arxiv.org/pdf/2312.10324","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389982907.pdf","grobid_xml":"https://content.openalex.org/works/W4389982907.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4298221930","https://openalex.org/W2777914285","https://openalex.org/W4287823391","https://openalex.org/W2770533869","https://openalex.org/W2888188966","https://openalex.org/W3208786872","https://openalex.org/W2990812465","https://openalex.org/W3038785057","https://openalex.org/W4287178147","https://openalex.org/W2165396616"],"abstract_inverted_index":{"Federated":[0],"learning":[1,19],"(FL)":[2],"with":[3,51,88],"noisy":[4,15,52,178],"labels":[5,16],"poses":[6],"a":[7,81,98,122,131,173],"significant":[8],"challenge.":[9],"Existing":[10],"methods":[11],"designed":[12],"for":[13,177],"handling":[14],"in":[17,25,77,143],"centralized":[18],"tend":[20],"to":[21,31,48,96],"lose":[22],"their":[23],"effectiveness":[24],"the":[26,32,37,67,104,154,165,181,191],"FL":[27,50],"setting,":[28],"mainly":[29],"due":[30],"small":[33],"dataset":[34],"size":[35],"and":[36,70,126,187],"heterogeneity":[38],"of":[39,73],"client":[40],"data.":[41,156],"While":[42],"some":[43],"attempts":[44],"have":[45],"been":[46],"made":[47],"tackle":[49],"labels,":[53,179],"they":[54],"primarily":[55],"focused":[56],"on":[57,153,185],"scenarios":[58],"involving":[59],"class-conditional":[60],"noise.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"study":[66],"more":[68],"challenging":[69],"practical":[71],"issue":[72],"instance-dependent":[74],"noise":[75],"(IDN)":[76],"FL.":[78],"We":[79],"introduce":[80],"novel":[82],"algorithm":[83],"called":[84],"FedBeat":[85,94],"(Federated":[86],"Learning":[87],"Bayesian":[89,132],"Ensemble-Assisted":[90],"Transition":[91],"Matrix":[92],"Estimation).":[93],"aims":[95],"build":[97],"global":[99,124,166],"statistically":[100],"consistent":[101],"classifier":[102,160],"using":[103,130,172],"IDN":[105],"transition":[106,139],"matrix":[107,140],"(IDNTM),":[108],"which":[109,144],"encompasses":[110],"three":[111],"synergistic":[112],"steps:":[113],"(1)":[114],"A":[115,137,158],"federated":[116,138,159],"data":[117,129],"extraction":[118],"step":[119,142,162],"that":[120,163,190],"constructs":[121],"weak":[123],"model":[125,133],"extracts":[127],"high-confidence":[128],"ensemble":[134],"method.":[135],"(2)":[136],"estimation":[141,150],"clients":[145],"collaboratively":[146],"train":[147],"an":[148],"IDNTM":[149],"network":[151],"based":[152],"extracted":[155],"(3)":[157],"correction":[161],"enhances":[164],"model's":[167],"performance":[168],"by":[169],"training":[170],"it":[171],"loss":[174],"function":[175],"tailored":[176],"leveraging":[180],"IDNTM.":[182],"Experiments":[183],"conducted":[184],"CIFAR-10":[186],"SVHN":[188],"verify":[189],"proposed":[192],"method":[193],"significantly":[194],"outperforms":[195],"state-of-the-art":[196],"methods.":[197]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}