{"id":"https://openalex.org/W7155357016","doi":"https://doi.org/10.48550/arxiv.2604.20825","title":"FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels","display_name":"FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155357016","doi":"https://doi.org/10.48550/arxiv.2604.20825"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.20825","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20825","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.20825","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123186276","display_name":"Sina Gholami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gholami, Sina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074152468","display_name":"Abdulmoneam Ali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali, Abdulmoneam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113191858","display_name":"Tania Haghighi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haghighi, Tania","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134411458","display_name":"Ahmed Arafa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arafa, Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072253597","display_name":"Minhaj Nur Alam","orcid":"https://orcid.org/0000-0003-3095-2232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alam, Minhaj Nur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.7023000121116638,"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":0.7023000121116638,"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":0.0689999982714653,"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":0.06620000302791595,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6234999895095825},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.597599983215332},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5860999822616577},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5296000242233276},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4961000084877014},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49459999799728394},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4260999858379364},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.40860000252723694},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.835099995136261},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6234999895095825},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.597599983215332},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5860999822616577},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5296000242233276},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4961000084877014},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47209998965263367},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42089998722076416},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.40860000252723694},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37380000948905945},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.20825","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20825","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.20825","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20825","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1,24],"(FL)":[2],"enables":[3],"collaborative":[4],"model":[5],"training":[6,130],"without":[7],"sharing":[8],"raw":[9],"data;":[10],"however,":[11],"the":[12,23,62,91],"presence":[13],"of":[14,65,78,94],"noisy":[15,39,87,110,162],"labels":[16],"across":[17],"distributed":[18],"clients":[19,88,104,111],"can":[20],"severely":[21],"degrade":[22],"performance.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,83,126],"propose":[30],"FedSIR,":[31],"a":[32,128],"multi-stage":[33],"framework":[34,76],"for":[35,159],"robust":[36],"FL":[37,150,160],"under":[38],"labels.":[40,163],"Different":[41],"from":[42],"existing":[43],"approaches":[44],"that":[45,108,132,153],"mainly":[46],"rely":[47],"on":[48,148],"designing":[49],"noise-tolerant":[50],"loss":[51,55],"functions":[52],"or":[53],"exploiting":[54],"dynamics":[56],"during":[57],"training,":[58],"our":[59],"method":[60],"leverages":[61],"spectral":[63,92,106],"structure":[64],"client":[66],"feature":[67,96],"representations":[68],"to":[69,112,141],"identify":[70,84],"and":[71,86,122,138],"mitigate":[72],"label":[73],"noise.":[74],"Our":[75],"consists":[77],"three":[79],"key":[80],"components.":[81],"First,":[82],"clean":[85,103],"by":[89],"analyzing":[90],"consistency":[93],"class-wise":[95],"subspaces":[97],"with":[98,161],"minimal":[99],"communication":[100],"overhead.":[101],"Second,":[102],"provide":[105],"references":[107],"enable":[109],"relabel":[113],"potentially":[114],"corrupted":[115],"samples":[116],"using":[117],"both":[118],"dominant":[119],"class":[120],"directions":[121],"residual":[123],"subspaces.":[124],"Third,":[125],"employ":[127],"noise-aware":[129],"strategy":[131],"integrates":[133],"logit-adjusted":[134],"loss,":[135],"knowledge":[136],"distillation,":[137],"distance-aware":[139],"aggregation":[140],"further":[142],"stabilize":[143],"federated":[144],"optimization.":[145],"Extensive":[146],"experiments":[147],"standard":[149],"benchmarks":[151],"demonstrate":[152],"FedSIR":[154],"consistently":[155],"outperforms":[156],"state-of-the-art":[157],"methods":[158],"The":[164],"code":[165],"is":[166],"available":[167],"at":[168],"https://github.com/sinagh72/FedSIR.":[169]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-24T00:00:00"}