{"id":"https://openalex.org/W7140133466","doi":"https://doi.org/10.48550/arxiv.2603.19722","title":"FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients","display_name":"FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7140133466","doi":"https://doi.org/10.48550/arxiv.2603.19722"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.19722","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19722","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.19722","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130386828","display_name":"Tian Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wen, Tian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130344498","display_name":"Zhiqin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhiqin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130360471","display_name":"Yonggang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yonggang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121525180","display_name":"Xuefeng Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xuefeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130324855","display_name":"Hao Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130327458","display_name":"Yuwei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130327757","display_name":"Bo Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Bo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5130386828"],"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":0.7652000188827515,"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":0.7652000188827515,"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":0.06949999928474426,"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":0.02810000069439411,"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/representation","display_name":"Representation (politics)","score":0.604200005531311},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.527899980545044},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5267999768257141},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5006999969482422},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4855000078678131},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4537999927997589},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4350999891757965},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41850000619888306},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.38420000672340393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7315000295639038},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.604200005531311},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.527899980545044},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4537999927997589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4510999917984009},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3750999867916107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3714999854564667},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C193519340","wikidata":"https://www.wikidata.org/wiki/Q891179","display_name":"Data loss","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.28619998693466187},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.19722","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19722","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.19722","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19722","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"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],"(FL)":[2],"suffers":[3],"from":[4,26,58],"performance":[5],"degradation":[6],"due":[7],"to":[8,76,99,107,122,164],"the":[9,27,128,142,147],"inevitable":[10],"presence":[11],"of":[12,72],"noisy":[13,24,37,78,138,162,184],"annotations":[14],"in":[15,22],"distributed":[16],"scenarios.":[17,50,186],"Existing":[18],"approaches":[19],"have":[20],"advanced":[21],"distinguishing":[23],"samples":[25,38,106,139],"dataset":[28],"for":[29,46,177],"label":[30],"correction":[31],"by":[32,85],"leveraging":[33],"loss":[34,43],"values.":[35],"However,":[36],"recognition":[39],"relying":[40],"on":[41,161],"scalar":[42],"lacks":[44],"reliability":[45],"FL":[47,178],"under":[48,65,182],"heterogeneous":[49],"In":[51],"this":[52,56,100],"paper,":[53],"we":[54,153],"rethink":[55],"paradigm":[57],"a":[59,92,117,124],"representation":[60],"perspective":[61],"and":[62,130,140],"propose":[63],"\\method~(\\textbf{Fed}erated":[64],"\\textbf{R}epresentation":[66],"\\textbf{G}emometry),":[67],"which":[68,135],"follows":[69],"\\textbf{the":[70],"principle":[71],"``representation":[73],"geometry":[74,101],"priority''}":[75],"recognize":[77],"labels.":[79],"Firstly,":[80],"\\method~creates":[81],"label-agnostic":[82],"spherical":[83,93],"representations":[84],"using":[86,102],"self-supervision.":[87],"It":[88],"then":[89],"iteratively":[90],"fits":[91],"von":[94],"Mises-Fisher":[95],"(vMF)":[96],"mixture":[97,144],"model":[98,145],"previously":[103],"identified":[104],"clean":[105,150],"capture":[108],"semantic":[109],"clusters.":[110],"This":[111],"geometric":[112],"evidence":[113],"is":[114],"integrated":[115],"with":[116,146,179],"semantic-label":[118],"soft":[119],"mapping":[120],"mechanism":[121],"derive":[123],"distribution":[125],"divergence":[126],"between":[127],"label-free":[129],"annotated":[131],"label-conditioned":[132],"feature":[133],"space,":[134],"robustly":[136],"identifies":[137],"updates":[141],"vMF":[143],"newly":[148],"separated":[149],"dataset.":[151],"Lastly,":[152],"employ":[154],"an":[155],"additional":[156],"personalized":[157],"noise":[158],"absorption":[159],"matrix":[160],"labels":[163],"achieve":[165],"robust":[166],"optimization.":[167],"Extensive":[168],"experimental":[169],"results":[170],"demonstrate":[171],"that":[172],"\\method~significantly":[173],"outperforms":[174],"state-of-the-art":[175],"methods":[176],"data":[180],"heterogeneity":[181],"diverse":[183],"clients":[185]},"counts_by_year":[],"updated_date":"2026-03-24T06:04:31.470712","created_date":"2026-03-24T00:00:00"}