{"id":"https://openalex.org/W7140032142","doi":"https://doi.org/10.1016/j.neunet.2026.108889","title":"Federated learning with noisy labels: A comprehensive and concise review of current methodologies and future directions","display_name":"Federated learning with noisy labels: A comprehensive and concise review of current methodologies and future directions","publication_year":2026,"publication_date":"2026-03-22","ids":{"openalex":"https://openalex.org/W7140032142","doi":"https://doi.org/10.1016/j.neunet.2026.108889","pmid":"https://pubmed.ncbi.nlm.nih.gov/41930546"},"language":"en","primary_location":{"id":"doi:10.1016/j.neunet.2026.108889","doi":"https://doi.org/10.1016/j.neunet.2026.108889","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.108889","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","doyens","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"volume":null,"type":"review","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neunet.2026.108889","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121264843","display_name":"Jia Dong","orcid":"https://orcid.org/0009-0004-5039-9547","observed_orcids":["https://orcid.org/0009-0004-5039-9547"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jia Dong","raw_affiliation_strings":["Department of Statistical Science, University College London, London, WC1E 6BT, UK. Electronic address: jia.dong.23@ucl.ac.uk"],"raw_orcid":"https://orcid.org/0009-0004-5039-9547","affiliations":[{"raw_affiliation_string":"Department of Statistical Science, University College London, London, WC1E 6BT, UK. Electronic address: jia.dong.23@ucl.ac.uk","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041649804","display_name":"Rui Zhu","orcid":"https://orcid.org/0000-0002-9944-0369","observed_orcids":["https://orcid.org/0000-0002-9944-0369"]},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142","https://openalex.org/I4401726869"]},{"id":"https://openalex.org/I4401726869","display_name":"City St George's, University of London","ror":"https://ror.org/047ybhc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I4401726869"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rui Zhu","raw_affiliation_strings":["Bayes Business School, City St George's, University of London, London, EC1Y 8TZ, UK"],"raw_orcid":"https://orcid.org/0000-0002-9944-0369","affiliations":[{"raw_affiliation_string":"Bayes Business School, City St George's, University of London, London, EC1Y 8TZ, UK","institution_ids":["https://openalex.org/I180825142","https://openalex.org/I4401726869"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098823733","display_name":"Xinyi Shang","orcid":"https://orcid.org/0000-0003-1147-1417","observed_orcids":["https://orcid.org/0000-0003-1147-1417"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinyi Shang","raw_affiliation_strings":["Department of Statistical Science, University College London, London, WC1E 6BT, UK"],"raw_orcid":"https://orcid.org/0000-0003-1147-1417","affiliations":[{"raw_affiliation_string":"Department of Statistical Science, University College London, London, WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079361172","display_name":"Jing\u2010Hao Xue","orcid":"https://orcid.org/0000-0003-1174-610X","observed_orcids":["https://orcid.org/0000-0003-1174-610X"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jing-Hao Xue","raw_affiliation_strings":["Department of Statistical Science, University College London, London, WC1E 6BT, UK"],"raw_orcid":"https://orcid.org/0000-0003-1174-610X","affiliations":[{"raw_affiliation_string":"Department of Statistical Science, University College London, London, WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5121264843"],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":{"value":3110,"currency":"USD","value_usd":3110},"apc_paid":{"value":3110,"currency":"USD","value_usd":3110},"fwci":0.9612,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74608783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"201","issue":null,"first_page":"108889","last_page":"108889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9688000082969666,"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":0.9688000082969666,"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":0.029999999329447746,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00019999999494757503,"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":0.9869999885559082},{"id":"https://openalex.org/keywords/noisy-labels","display_name":"label noise","score":0.9539999961853027},{"id":"https://openalex.org/keywords/noisy-label-learning","display_name":"noisy label learning","score":0.8479999899864197},{"id":"https://openalex.org/keywords/client-heterogeneity","display_name":"client heterogeneity","score":0.671999990940094},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.8579999804496765},{"id":"https://openalex.org/keywords/privacy-preserving-machine-learning","display_name":"privacy-preserving machine learning","score":0.7020000219345093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029000163078308},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7019000053405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5612000226974487},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5098000168800354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4862000048160553},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.2563000023365021}],"mesh":[{"descriptor_ui":"D000097786","descriptor_name":"Soft Computing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098407","descriptor_name":"Federated Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1016/j.neunet.2026.108889","doi":"https://doi.org/10.1016/j.neunet.2026.108889","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.108889","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","doyens","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},{"id":"pmid:41930546","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41930546","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural networks : the official journal of the International Neural Network Society","raw_type":"Journal Article"},{"id":"pmh:oai:openaccess.city.ac.uk:37433","doi":null,"is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/rui=2Ezhu.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/37433/1/1-s2.0-S0893608026003503-main.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"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":"Article"}],"best_oa_location":{"id":"doi:10.1016/j.neunet.2026.108889","doi":"https://doi.org/10.1016/j.neunet.2026.108889","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.108889","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","doyens","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W3042609801","https://openalex.org/W3108055363","https://openalex.org/W3215126987","https://openalex.org/W4200046178","https://openalex.org/W4223522460","https://openalex.org/W4286564958","https://openalex.org/W4323670134","https://openalex.org/W4386322030","https://openalex.org/W4387105517","https://openalex.org/W4387339740","https://openalex.org/W4387460392","https://openalex.org/W4389454722","https://openalex.org/W4389937392","https://openalex.org/W4394779364","https://openalex.org/W4396782851","https://openalex.org/W4400529443","https://openalex.org/W4401942485","https://openalex.org/W4402045967","https://openalex.org/W4404249785","https://openalex.org/W4404766664","https://openalex.org/W4404914692","https://openalex.org/W4406525809","https://openalex.org/W4406921686","https://openalex.org/W4407742619","https://openalex.org/W4408240727","https://openalex.org/W4409193913","https://openalex.org/W4409257405","https://openalex.org/W4411300744","https://openalex.org/W4411449417","https://openalex.org/W4414535396"],"related_works":["https://openalex.org/W4387460392","https://openalex.org/W7160898533","https://openalex.org/W4386322030","https://openalex.org/W4393160141","https://openalex.org/W4281384403","https://openalex.org/W4408240727","https://openalex.org/W4402045967","https://openalex.org/W4392152284","https://openalex.org/W7125912646","https://openalex.org/W4309201601"],"abstract_inverted_index":{"Federated":[0],"learning,":[1,8,26,33,67],"a":[2,72,116],"vital":[3,28],"paradigm":[4,29],"in":[5,30,86],"modern":[6,31],"machine":[7,32,66],"enables":[9],"private":[10],"and":[11,110,138,147,164],"decentralised":[12],"training":[13,36],"of":[14,37,65,74,80,102],"models":[15,38],"that":[16,126],"is":[17,55,83],"crucial":[18],"for":[19,160],"learning":[20,50],"from":[21,39,62],"sensitive":[22],"data.":[23],"Noisy":[24],"label":[25,98,103,108],"another":[27],"addresses":[34],"the":[35,40,63,128,144],"data":[41],"with":[42,51],"potentially":[43],"incorrect":[44],"labels.":[45],"Their":[46],"integration,":[47],"namely":[48],"federated":[49],"noisy":[52],"labels":[53],"(FLNL),":[54],"an":[56],"emerging":[57],"but":[58],"challenging":[59],"topic":[60],"arising":[61],"practice":[64],"which,":[68],"however,":[69],"still":[70],"lacks":[71],"review":[73,149],"its":[75],"research":[76,158],"progress.":[77],"The":[78],"aim":[79],"this":[81,87,161],"paper":[82],"to":[84,95,107,118,151],"fill":[85],"gap.":[88],"We":[89,113],"first":[90,145],"summarise":[91],"four":[92,124,129],"core":[93],"challenges":[94,130],"FLNL:":[96],"localised":[97,105],"noise,":[99,104,109],"across-client":[100],"heterogeneity":[101],"overfitting":[106],"inadequate":[111],"benchmarking.":[112],"then":[114],"propose":[115],"taxonomy":[117],"categorise":[119],"current":[120],"FLNL":[121],"studies":[122],"into":[123],"types":[125],"address":[127],"correspondingly:":[131],"sample-wise":[132],"methods,":[133,135,137],"client-wise":[134],"model-wise":[136],"benchmark-wise":[139],"studies.":[140],"This":[141],"work":[142],"offers":[143],"comprehensive":[146],"concise":[148],"dedicated":[150],"FLNL;":[152],"moreover,":[153],"we":[154],"also":[155],"provide":[156],"future":[157],"directions":[159],"rapidly":[162],"evolving":[163],"practically":[165],"significant":[166],"field.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-03-23T00:00:00"}