{"id":"https://openalex.org/W7133764287","doi":"https://doi.org/10.48550/arxiv.2603.04062","title":"FedCova: Robust Federated Covariance Learning Against Noisy Labels","display_name":"FedCova: Robust Federated Covariance Learning Against Noisy Labels","publication_year":2026,"publication_date":"2026-03-04","ids":{"openalex":"https://openalex.org/W7133764287","doi":"https://doi.org/10.48550/arxiv.2603.04062"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.04062","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128216405","display_name":"Xiangyu Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhong, Xiangyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103286633","display_name":"Yi Ma","orcid":"https://orcid.org/0000-0003-1955-6853"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Xiaojun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128174260","display_name":"Ying-Jun Angela Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ying-Jun Angela","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5128216405"],"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":0.7875000238418579,"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":0.7875000238418579,"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":0.03869999945163727,"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":0.028699999675154686,"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":0.7093999981880188},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6917999982833862},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6780999898910522},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.48750001192092896},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46700000762939453},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.46129998564720154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42910000681877136},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.40470001101493835},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4000999927520752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597000002861023},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7093999981880188},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6917999982833862},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6780999898910522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5561000108718872},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48730000853538513},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4140999913215637},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.30320000648498535},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.04062","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.04062","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.04062","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":"pmh:doi:10.48550/arxiv.2603.04062","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.43896588683128357,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Noisy":[0],"labels":[1,153],"in":[2,15],"distributed":[3],"datasets":[4],"induce":[5],"severe":[6],"local":[7],"overfitting":[8],"and":[9,149,164,176],"consequently":[10],"compromise":[11],"the":[12,36,60,131,135,146,182,189],"global":[13],"model":[14,37],"federated":[16,49,97,123],"learning":[17,51],"(FL).":[18],"Most":[19],"existing":[20],"solutions":[21],"rely":[22],"on":[23,68,87,104,155,174],"selecting":[24],"clean":[25,31],"devices":[26],"or":[27],"aligning":[28],"with":[29,39,108,188],"public":[30],"datasets,":[32],"rather":[33],"than":[34],"endowing":[35],"itself":[38],"robustness.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,91,119],"propose":[45],"FedCova,":[46],"a":[47,65,76,93,121,142],"dependency-free":[48],"covariance":[50],"framework":[52],"that":[53,101],"eliminates":[54],"such":[55],"external":[56],"reliances":[57],"by":[58,117],"enhancing":[59],"model's":[61],"intrinsic":[62],"robustness":[63,184],"via":[64],"new":[66],"perspective":[67],"feature":[69,80,99,106,114,138,156],"covariances.":[70],"Specifically,":[71],"FedCova":[72,125,160,186],"encodes":[73],"data":[74,170],"into":[75],"discriminative":[77],"but":[78],"resilient":[79],"space":[81],"to":[82],"tolerate":[83],"label":[84],"noise.":[85],"Built":[86],"mutual":[88],"information":[89],"maximization,":[90],"design":[92],"novel":[94],"objective":[95],"for":[96,137],"lossy":[98],"encoding":[100],"relies":[102],"solely":[103],"class":[105],"covariances":[107],"an":[109],"error":[110],"tolerance":[111],"term.":[112],"Leveraging":[113],"subspaces":[115],"characterized":[116],"covariances,":[118],"construct":[120],"subspace-augmented":[122],"classifier.":[124],"unifies":[126],"three":[127],"key":[128],"processes":[129],"through":[130],"covariance:":[132],"(1)":[133],"training":[134],"network":[136],"encoding,":[139],"(2)":[140],"constructing":[141],"classifier":[143],"directly":[144],"from":[145],"learned":[147],"features,":[148],"(3)":[150],"correcting":[151],"noisy":[152,166,178],"based":[154],"subspaces.":[157],"We":[158],"implement":[159],"across":[161],"both":[162],"symmetric":[163],"asymmetric":[165],"settings":[167],"under":[168],"heterogeneous":[169],"distribution.":[171],"Experimental":[172],"results":[173],"CIFAR-10/100":[175],"real-world":[177],"dataset":[179],"Clothing1M":[180],"demonstrate":[181],"superior":[183],"of":[185],"compared":[187],"state-of-the-art":[190],"methods.":[191]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-03-06T00:00:00"}