{"id":"https://openalex.org/W4408954476","doi":"https://doi.org/10.23919/icact63878.2025.10936775","title":"Relaxed Contrastive Learning for Robust Federated Models with Noisy Labels and Limited Clients","display_name":"Relaxed Contrastive Learning for Robust Federated Models with Noisy Labels and Limited Clients","publication_year":2025,"publication_date":"2025-02-16","ids":{"openalex":"https://openalex.org/W4408954476","doi":"https://doi.org/10.23919/icact63878.2025.10936775"},"language":"en","primary_location":{"id":"doi:10.23919/icact63878.2025.10936775","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icact63878.2025.10936775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 27th International Conference on Advanced Communications Technology (ICACT)","raw_type":"proceedings-article"},"type":"conference-paper","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":["Kyung Hee University,Department of Computer Science and Engineering,Yongin,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University,Department of Computer Science and Engineering,Yongin,South Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021511574","display_name":"Apurba Adhikary","orcid":"https://orcid.org/0000-0003-3970-1878"},"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":"Apurba Adhikary","raw_affiliation_strings":["Kyung Hee University,Department of Computer Science and Engineering,Yongin,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University,Department of Computer Science and Engineering,Yongin,South 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":["Kyung Hee University,Department of Computer Science and Engineering,Yongin,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University,Department of Computer Science and Engineering,Yongin,South 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":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9997000098228455,"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":0.9997000098228455,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9890000224113464,"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":0.9887999892234802,"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":0.8169044256210327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5146849751472473},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4642731845378876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39254218339920044},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34066489338874817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169044256210327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5146849751472473},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4642731845378876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39254218339920044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34066489338874817}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/icact63878.2025.10936775","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icact63878.2025.10936775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 27th International Conference on Advanced Communications Technology (ICACT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2594481151","https://openalex.org/W2750384547","https://openalex.org/W2981873476","https://openalex.org/W3107078643","https://openalex.org/W3182158470","https://openalex.org/W4287947470","https://openalex.org/W4290875695","https://openalex.org/W4312231739","https://openalex.org/W4312403682","https://openalex.org/W4318619660","https://openalex.org/W4388820684","https://openalex.org/W4389252625","https://openalex.org/W4402702992","https://openalex.org/W6703116779","https://openalex.org/W6728757088","https://openalex.org/W6743688258","https://openalex.org/W6745136726","https://openalex.org/W6759238902","https://openalex.org/W6773817997","https://openalex.org/W6787972765","https://openalex.org/W6843055207","https://openalex.org/W6847216410"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3176937389","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4408069290","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694"],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"enables":[2],"collaborative":[3],"model":[4,31],"training":[5],"across":[6],"distributed":[7],"clients":[8],"without":[9],"sharing":[10],"raw":[11],"data,":[12],"making":[13,115],"it":[14,116],"suitable":[15],"for":[16,119],"privacy-sensitive":[17],"applications.":[18],"However,":[19],"FL":[20],"faces":[21],"significant":[22],"challenges":[23],"due":[24],"to":[25,58,137],"noisy":[26,60],"labels,":[27],"which":[28],"can":[29],"degrade":[30],"performance,":[32],"especially":[33],"in":[34],"non-IID":[35],"environments.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"propose":[41],"a":[42,53,125,134],"robust":[43],"federated":[44,139],"learning":[45],"method":[46,92,105],"that":[47,90],"combines":[48],"symmetric":[49,82],"cross-entropy":[50],"loss":[51,57],"with":[52,110],"modified":[54],"relaxed":[55],"contrastive":[56],"address":[59],"labels":[61],"and":[62,77,83,101,129],"improve":[63],"the":[64],"diversity":[65],"of":[66],"learned":[67],"feature":[68],"representations.":[69],"We":[70],"evaluate":[71],"our":[72,91,104,132],"approach":[73,133],"on":[74],"Fashion-MNIST,":[75],"SVHN,":[76],"CIFAR-10":[78],"datasets":[79],"under":[80],"both":[81],"asymmetric":[84],"noise":[85],"settings.":[86],"The":[87],"results":[88],"demonstrate":[89],"consistently":[93],"outperforms":[94],"multiple":[95],"baselines,":[96],"including":[97],"FedAvg,":[98],"FedProx,":[99],"FedMixup,":[100],"FedLSR.":[102],"Notably,":[103],"shows":[106],"strong":[107],"performance":[108],"even":[109],"low":[111],"client":[112],"participation":[113],"rates,":[114],"highly":[117],"effective":[118],"scenarios":[120],"where":[121],"communication":[122],"cost":[123],"is":[124],"concern.":[126],"This":[127],"robustness":[128],"efficiency":[130],"make":[131],"valuable":[135],"contribution":[136],"noise-robust":[138],"learning.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}