{"id":"https://openalex.org/W4309201601","doi":"https://doi.org/10.48550/arxiv.2211.07816","title":"Quantifying the Impact of Label Noise on Federated Learning","display_name":"Quantifying the Impact of Label Noise on Federated Learning","publication_year":2022,"publication_date":"2022-11-15","ids":{"openalex":"https://openalex.org/W4309201601","doi":"https://doi.org/10.48550/arxiv.2211.07816"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.07816","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.07816","pdf_url":"https://arxiv.org/pdf/2211.07816","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.07816","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079616969","display_name":"Shuqi Ke","orcid":"https://orcid.org/0000-0002-2467-6502","observed_orcids":["https://orcid.org/0000-0002-2467-6502"]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke, Shuqi","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091518548","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0002-2062-1512","observed_orcids":["https://orcid.org/0000-0002-2062-1512"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Chao","raw_affiliation_strings":["University of California , Davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100352274","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-8272-9553","observed_orcids":["https://orcid.org/0000-0002-8272-9553"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Xin","raw_affiliation_strings":["University of California , Davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Davis","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9872999787330627,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9872999787330627,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.011699999682605267,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0003000000142492354,"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/federated-learning","display_name":"federated learning","score":0.9739999771118164},{"id":"https://openalex.org/keywords/noisy-labels","display_name":"label noise","score":1.0},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.9100000262260437},{"id":"https://openalex.org/keywords/generalization-error","display_name":"generalization error","score":0.7609999775886536},{"id":"https://openalex.org/keywords/upper-bounds","display_name":"upper bounds","score":0.6000000238418579},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.656000018119812},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.9879999756813049},{"id":"https://openalex.org/keywords/data-heterogeneity","display_name":"data heterogeneity","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9276838302612305},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8099712133407593},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7483530044555664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6846870183944702},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6023537516593933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.534955620765686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5064460039138794},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4473947584629059},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.431151419878006},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3323034346103668},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3202725648880005},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26876819133758545},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17177584767341614},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12943625450134277},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.07816","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.07816","pdf_url":"https://arxiv.org/pdf/2211.07816","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.2211.07816","doi":"https://doi.org/10.48550/arxiv.2211.07816","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.07816","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:2211.07816","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.07816","pdf_url":"https://arxiv.org/pdf/2211.07816","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/G1162667442","display_name":"Track-D: Data-Driven Disease Prevention and Control in Animal Health","funder_award_id":"2134901","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1851784936","display_name":null,"funder_award_id":"2020\u201367021-32855","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"},{"id":"https://openalex.org/G2958765513","display_name":null,"funder_award_id":"2020-67021-32855","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3789803274","display_name":"BIGDATA: IA: A multi-level approach for global optimization of the surveillance and control of infectious disease in the swine industry","funder_award_id":"1838207","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3841099640","display_name":"CNS Core: Medium: Collaborative:  Exploring and Exploiting Learning for Efficient Network Control: Non-Stationarity,  Inter-Dependence, and Domain-Knowledge","funder_award_id":"1901218","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5620962805","display_name":null,"funder_award_id":"67021","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332299","display_name":"National Institute of Food and Agriculture","ror":"https://ror.org/05qx3fv49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390098255","https://openalex.org/W4386322030","https://openalex.org/W4387460392","https://openalex.org/W4393160141","https://openalex.org/W7161582877","https://openalex.org/W4402045967","https://openalex.org/W7140032142","https://openalex.org/W4393159546","https://openalex.org/W4403582721","https://openalex.org/W7135080169"],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"is":[3,45,77,115,145],"a":[4,13,56],"distributed":[5],"machine":[6],"learning":[7],"paradigm":[8],"where":[9],"clients":[10],"collaboratively":[11],"train":[12],"model":[14,105,137],"using":[15,94],"their":[16],"local":[17],"(human-generated)":[18],"datasets.":[19],"While":[20],"existing":[21],"studies":[22],"focus":[23],"on":[24,59,65,89],"FL":[25,44,96,132],"algorithm":[26],"development":[27],"to":[28,50,139],"tackle":[29],"data":[30,38],"heterogeneity":[31],"across":[32],"clients,":[33],"the":[34,60,73,80,103,110,129,135,142],"important":[35],"issue":[36],"of":[37,62,131],"quality":[39],"(e.g.,":[40],"label":[41,63,82,125],"noise)":[42],"in":[43,79],"overlooked.":[46],"This":[47],"paper":[48],"aims":[49],"fill":[51],"this":[52],"gap":[53],"by":[54],"providing":[55],"quantitative":[57],"study":[58],"impact":[61],"noise":[64,83,111,126,143],"FL.":[66],"We":[67,121],"derive":[68],"an":[69],"upper":[70],"bound":[71],"for":[72],"generalization":[74],"error":[75],"that":[76,102,124],"linear":[78],"clients'":[81],"level.":[84],"Then":[85],"we":[86],"conduct":[87],"experiments":[88],"MNIST":[90],"and":[91,134],"CIFAR-10":[92],"datasets":[93],"various":[95],"algorithms.":[97],"Our":[98],"empirical":[99],"results":[100],"show":[101],"global":[104,136],"accuracy":[106],"linearly":[107],"decreases":[108],"as":[109],"level":[112,144],"increases,":[113],"which":[114],"consistent":[116],"with":[117],"our":[118],"theoretical":[119],"analysis.":[120],"further":[122],"find":[123],"slows":[127],"down":[128],"convergence":[130],"training,":[133],"tends":[138],"overfit":[140],"when":[141],"high.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2022-11-24T00:00:00"}