{"id":"https://openalex.org/W4414270202","doi":"https://doi.org/10.1109/tai.2025.3609745","title":"Mitigating Label Noise in Federated Learning With Regularized Features and Robust Loss","display_name":"Mitigating Label Noise in Federated Learning With Regularized Features and Robust Loss","publication_year":2025,"publication_date":"2025-09-17","ids":{"openalex":"https://openalex.org/W4414270202","doi":"https://doi.org/10.1109/tai.2025.3609745"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3609745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3609745","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-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/A5082747877","display_name":"Girum Fitihamlak Ejigu","orcid":"https://orcid.org/0000-0002-1080-653X"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Girum Fitihamlak Ejigu","raw_affiliation_strings":["Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Republic of Korea","Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Rep. of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1080-653X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Rep. of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685794","display_name":"Ki Tae Kim","orcid":"https://orcid.org/0000-0002-5692-1189"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kitae Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Republic of Korea","Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Rep. of Korea"],"raw_orcid":"https://orcid.org/0000-0002-5692-1189","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Rep. of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034052371","display_name":"Choong Seon Hong","orcid":"https://orcid.org/0000-0003-3484-7333"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Choong Seon Hong","raw_affiliation_strings":["Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Republic of Korea","Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Rep. of Korea"],"raw_orcid":"https://orcid.org/0000-0003-3484-7333","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do, Rep. of Korea","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35928602"],"apc_list":null,"apc_paid":null,"fwci":4.188,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94296145,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"7","issue":"4","first_page":"2012","last_page":"2023"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9891999959945679,"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":0.9891999959945679,"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":0.6976000070571899},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.695900022983551},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6500999927520752},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.6500999927520752},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.5371999740600586},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5105999708175659},{"id":"https://openalex.org/keywords/artificial-noise","display_name":"Artificial noise","score":0.4745999872684479},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4717000126838684},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4625999927520752},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.429500013589859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003000020980835},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6976000070571899},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.695900022983551},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6500999927520752},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6500999927520752},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5404999852180481},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5139999985694885},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5105999708175659},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.4745999872684479},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4625999927520752},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3792000114917755},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3125},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3609745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3609745","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1921293667","https://openalex.org/W2194775991","https://openalex.org/W2964274690","https://openalex.org/W2981873476","https://openalex.org/W2982409974","https://openalex.org/W3021654819","https://openalex.org/W3133814152","https://openalex.org/W3182158470","https://openalex.org/W3187784948","https://openalex.org/W4212881588","https://openalex.org/W4229049252","https://openalex.org/W4287947470","https://openalex.org/W4290875695","https://openalex.org/W4293791267","https://openalex.org/W4295806247","https://openalex.org/W4307823382","https://openalex.org/W4312231739","https://openalex.org/W4312403682","https://openalex.org/W4312517097","https://openalex.org/W4312950667","https://openalex.org/W4313325044","https://openalex.org/W4320017490","https://openalex.org/W4321488579","https://openalex.org/W4361761348","https://openalex.org/W4385767857","https://openalex.org/W4387460392","https://openalex.org/W4387968262","https://openalex.org/W4388820684","https://openalex.org/W4389352566","https://openalex.org/W4389937392","https://openalex.org/W4390938718","https://openalex.org/W4391145952","https://openalex.org/W4392904009","https://openalex.org/W4393149358","https://openalex.org/W4393160141","https://openalex.org/W4404914692","https://openalex.org/W4405022532","https://openalex.org/W4405746536","https://openalex.org/W4408240727","https://openalex.org/W4408954476"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"enables":[2],"decentralized":[3],"model":[4,34],"training":[5],"across":[6,91],"distributed":[7],"devices":[8],"while":[9],"preserving":[10],"data":[11,23],"privacy":[12],"and":[13,24,64,88,109,122,128,143,152],"reducing":[14],"communication":[15],"overhead.":[16],"However,":[17],"the":[18,54,84,123,150],"presence":[19],"of":[20,57,86,154],"heterogeneous":[21],"client":[22],"noisy":[25,110,125],"labels":[26],"poses":[27],"significant":[28],"challenges,":[29],"often":[30],"leading":[31],"to":[32,52,82,100],"degraded":[33],"performance,":[35],"especially":[36],"in":[37,156],"communication-constrained":[38],"environments.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,94],"propose":[44],"FedRFRL,":[45],"a":[46,65,72,78],"robust":[47,66],"federated":[48,158],"learning":[49,85,159],"framework":[50],"designed":[51],"mitigate":[53],"adverse":[55],"effects":[56],"label":[58,145],"noise":[59],"by":[60],"combining":[61],"feature":[62],"regularization":[63,74],"loss":[67],"function.":[68],"Specifically,":[69],"FedRFRL":[70,132,155],"introduces":[71],"representation":[73],"strategy":[75],"that":[76,131],"leverages":[77],"high-dimensional":[79],"projection":[80],"layer":[81],"promote":[83],"diverse":[87],"discriminative":[89],"features":[90],"clients.":[92],"Additionally,":[93],"incorporate":[95],"adaptive":[96],"sharpness-aware":[97],"minimization":[98],"(ASAM)":[99],"encourage":[101],"flatter":[102],"minima":[103],"for":[104],"improved":[105],"generalization":[106],"under":[107],"non-IID":[108],"settings.":[111],"Extensive":[112],"experiments":[113],"on":[114],"benchmark":[115],"datasets,":[116],"including":[117],"CIFAR-10,":[118],"CIFAR-100,":[119],"SVHN,":[120],"Fashion-MNIST,":[121],"real-world":[124,157],"datasets":[126],"CIFAR-N":[127],"Clothing1M,":[129],"demonstrate":[130],"consistently":[133],"outperforms":[134],"existing":[135],"methods,":[136],"achieving":[137],"strong":[138],"robustness":[139],"against":[140],"both":[141],"symmetric":[142],"asymmetric":[144],"noise.":[146],"These":[147],"results":[148],"highlight":[149],"effectiveness":[151],"scalability":[153],"scenarios":[160],"with":[161],"imperfect":[162],"supervision.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}