{"id":"https://openalex.org/W7139020751","doi":"https://doi.org/10.23919/icact68090.2026.11431311","title":"FSANL: Symmetric Active Negative Loss for Robust Federated Learning Under Heterogeneous Label Noise","display_name":"FSANL: Symmetric Active Negative Loss for Robust Federated Learning Under Heterogeneous Label Noise","publication_year":2026,"publication_date":"2026-02-08","ids":{"openalex":"https://openalex.org/W7139020751","doi":"https://doi.org/10.23919/icact68090.2026.11431311"},"language":null,"primary_location":{"id":"doi:10.23919/icact68090.2026.11431311","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icact68090.2026.11431311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 28th 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,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University,Department of Computer Science and Engineering,Yongin,Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046015188","display_name":"Avi Deb Raha","orcid":"https://orcid.org/0000-0003-0240-1214"},"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":"Avi Deb Raha","raw_affiliation_strings":["Kyung Hee University,Department of Computer Science and Engineering,Yongin,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University,Department of Computer Science and Engineering,Yongin,Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088612895","display_name":"Mrityunjoy Gain","orcid":"https://orcid.org/0000-0002-1771-0100"},"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":"Mrityunjoy Gain","raw_affiliation_strings":["Kyung Hee University,Department of Artificial Intelligence,Yongin,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University,Department of Artificial Intelligence,Yongin,Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130166053","display_name":"Choong Seon Hong","orcid":null},"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,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University,Department of Computer Science and Engineering,Yongin,Republic 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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.4684000015258789,"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":0.4684000015258789,"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":0.1151999980211258,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.1071000024676323,"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":0.7616999745368958},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7195000052452087},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46869999170303345},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.36070001125335693},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.31310001015663147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858999967575073},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7616999745368958},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7195000052452087},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47530001401901245},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46869999170303345},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37299999594688416},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/icact68090.2026.11431311","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icact68090.2026.11431311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 28th International Conference on Advanced Communications Technology (ICACT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4979041730","display_name":null,"funder_award_id":"RS-202300207816,RS-2024-00352423","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2765407302","https://openalex.org/W2981873476","https://openalex.org/W3133814152","https://openalex.org/W3182158470","https://openalex.org/W4229029907","https://openalex.org/W4312403682","https://openalex.org/W4312517097","https://openalex.org/W4321488579","https://openalex.org/W4327927980","https://openalex.org/W4389105454","https://openalex.org/W4408240727","https://openalex.org/W4408954476","https://openalex.org/W4413147146","https://openalex.org/W4414270202","https://openalex.org/W7133212323"],"related_works":[],"abstract_inverted_index":{"Federated":[0,87],"learning":[1],"(FL)":[2],"enables":[3],"collaborative":[4],"model":[5],"training":[6],"across":[7],"decentralized":[8],"clients":[9],"while":[10,36],"preserving":[11],"data":[12,23],"privacy.":[13],"However,":[14],"real-world":[15],"FL":[16,56],"deployments":[17],"often":[18],"face":[19],"two":[20],"major":[21],"challenges:":[22],"heterogeneity":[24],"and":[25,115,146,151],"label":[26,105,153],"noise.":[27],"The":[28],"former":[29],"arises":[30],"due":[31],"to":[32,100,130],"non-IID":[33,150],"client":[34,65,132],"distributions,":[35],"the":[37,52,70],"latter":[38],"results":[39],"from":[40],"user-generated":[41],"annotations,":[42],"sensor":[43],"failures,":[44],"or":[45,68],"distribution":[46],"shifts,":[47],"conditions":[48],"that":[49,139],"severely":[50],"degrade":[51],"performance":[53],"of":[54,72],"standard":[55],"algorithms.":[57],"Existing":[58],"approaches":[59],"typically":[60],"rely":[61],"on":[62,136],"multi-stage":[63],"training,":[64],"selection":[66],"strategies,":[67],"assume":[69],"presence":[71],"clean":[73,110],"clients,":[74],"which":[75],"may":[76],"not":[77],"hold":[78],"in":[79],"realistic":[80],"settings.":[81],"In":[82],"this":[83],"work,":[84],"we":[85],"propose":[86],"Symmetric":[88],"Active":[89],"Negative":[90],"Loss":[91],"(FSANL),":[92],"a":[93],"simple":[94],"yet":[95],"effective":[96],"single-stage":[97],"framework":[98],"designed":[99],"improve":[101],"robustness":[102],"under":[103,148],"heterogeneous":[104],"noise":[106],"without":[107],"assuming":[108],"any":[109],"clients.":[111],"FSANL":[112,140],"integrates":[113],"normalized":[114],"symmetric":[116],"cross-entropy":[117],"losses":[118],"with":[119,126],"an":[120],"active":[121],"negative":[122],"suppression":[123],"term,":[124],"along":[125],"global":[127],"L1":[128],"regularization":[129],"counteract":[131],"drift.":[133],"Extensive":[134],"experiments":[135],"CIFAR-10":[137],"demonstrate":[138],"outperforms":[141],"existing":[142],"baselines,":[143],"including":[144],"FedCorr":[145],"FedProx,":[147],"various":[149],"noisy":[152],"scenarios.":[154]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-20T00:00:00"}