{"id":"https://openalex.org/W7221522822","doi":"https://doi.org/10.48550/arxiv.2610.13631","title":"Private and Distributionally Robust Federated Multiclass Classification","display_name":"Private and Distributionally Robust Federated Multiclass Classification","publication_year":2026,"publication_date":"2026-10-09","ids":{"openalex":"https://openalex.org/W7221522822","doi":"https://doi.org/10.48550/arxiv.2610.13631"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.13631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.13631","pdf_url":"https://arxiv.org/pdf/2610.13631","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.13631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063875716","display_name":"Andrea Paulette Hern\u00e1ndez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hernandez, Andrea P.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124385218","display_name":"Michael Ibrahim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ibrahim, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054372641","display_name":"Nagi Gebraeel","orcid":"https://orcid.org/0000-0001-7337-2401","observed_orcids":["https://orcid.org/0000-0001-7337-2401"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gebraeel, Nagi","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":true,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0,"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":0.0,"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":0.9330000281333923},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"differential privacy","score":0.9150000214576721},{"id":"https://openalex.org/keywords/distributionally-robust-optimization","display_name":"distributionally robust optimization","score":0.9570000171661377},{"id":"https://openalex.org/keywords/multiclass-classification","display_name":"multi-class classification","score":0.9240000247955322},{"id":"https://openalex.org/keywords/noisy-labels","display_name":"label noise","score":0.7139999866485596},{"id":"https://openalex.org/keywords/privacy-utility-trade-off","display_name":"privacy-utility trade-off","score":0.9229999780654907},{"id":"https://openalex.org/keywords/industrial-fault-diagnosis","display_name":"industrial fault diagnosis","score":0.8410000205039978},{"id":"https://openalex.org/keywords/alternating-direction-method-of-multipliers","display_name":"alternating direction method of multipliers","score":0.75}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843999862670898},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6133999824523926},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C123860398","wikidata":"https://www.wikidata.org/wiki/Q6934605","display_name":"Multiclass classification","level":3,"score":0.44859999418258667},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4456999897956848},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4205999970436096},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4194999933242798},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.39160001277923584},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.3723999857902527},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33640000224113464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.2734000086784363}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.13631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.13631","pdf_url":"https://arxiv.org/pdf/2610.13631","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.13631","doi":"https://doi.org/10.48550/arxiv.2610.13631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.13631","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.13631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.13631","pdf_url":"https://arxiv.org/pdf/2610.13631","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221522822.pdf","grobid_xml":"https://content.openalex.org/works/W7221522822.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4403928971","https://openalex.org/W4416114117"],"related_works":["https://openalex.org/W2990239018","https://openalex.org/W7214751429","https://openalex.org/W4312992469","https://openalex.org/W4308114370","https://openalex.org/W7128400846","https://openalex.org/W7154969499","https://openalex.org/W4406728192","https://openalex.org/W4401836692","https://openalex.org/W4321488579","https://openalex.org/W4361759834"],"abstract_inverted_index":{"Fault":[0],"diagnosis":[1],"in":[2,197],"asset-intensive":[3],"industries":[4],"requires":[5],"multiclass":[6,63,83],"models":[7],"trained":[8],"on":[9,77,172],"noisy,":[10],"sensitive":[11],"data":[12,176],"collected":[13],"across":[14,158],"geographically":[15],"distributed":[16],"client":[17,41,103,115],"sites.":[18],"Federated":[19],"learning":[20],"enables":[21],"collaborative":[22],"training":[23,160],"without":[24],"centralizing":[25],"data,":[26],"but":[27],"most":[28,198],"approaches":[29],"do":[30],"not":[31],"provide":[32,146],"formal":[33],"privacy":[34,68,139,150,156],"guarantees":[35,151],"for":[36,61,69],"individual":[37],"records":[38,70],"stored":[39,71],"at":[40,72,130],"sites":[42],"and":[43,122,134,152,166,177,192],"can":[44],"degrade":[45],"under":[46,205],"label":[47],"noise.":[48,208],"To":[49,99],"address":[50],"these":[51],"limitations,":[52],"we":[53,135],"develop":[54],"a":[55,78],"differentially":[56,186],"private,":[57],"distributionally":[58,81,125],"robust":[59,82,126],"framework":[60],"federated":[62,79,188],"classification":[64],"that":[65,182],"provides":[66],"sample-level":[67,148],"each":[73],"client.":[74],"We":[75,145],"build":[76],"Wasserstein":[80],"objective":[84],"with":[85,163,201],"the":[86,101,112,119,123,131,137,142,202],"Crammer-Singer":[87],"loss,":[88],"solved":[89],"using":[90,141],"an":[91,153,167],"Alternating":[92],"Direction":[93],"Method":[94],"of":[95,117],"Multipliers":[96],"(ADMM)-based":[97],"algorithm.":[98],"protect":[100],"released":[102],"updates,":[104],"our":[105,183],"method":[106,184],"injects":[107],"calibrated":[108],"Gaussian":[109],"noise":[110],"into":[111],"proximal":[113],"linearized":[114],"updates":[116],"both":[118],"local":[120,124],"model":[121],"variable":[127],"before":[128],"aggregation":[129],"central":[132],"server,":[133],"quantify":[136],"cumulative":[138],"loss":[140],"moments":[143],"accountant.":[144],"per-round":[147],"$(\u03b5,\u03b4)$-differential":[149],"overall":[154],"composed":[155],"guarantee":[157],"all":[159],"rounds,":[161],"together":[162],"convergence":[164],"results":[165],"explicit":[168],"privacy-utility":[169],"tradeoff.":[170],"Experiments":[171],"simulated":[173],"industrial":[174],"fault":[175],"UCI":[178],"benchmark":[179],"datasets":[180],"show":[181],"outperforms":[185],"private":[187],"empirical":[189],"risk":[190],"minimization":[191],"stochastic":[193],"gradient":[194],"descent":[195],"baselines":[196],"tested":[199],"settings,":[200],"largest":[203],"gains":[204],"strong":[206],"privacy-induced":[207]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-13T00:00:00"}