{"id":"https://openalex.org/W7131816323","doi":"https://doi.org/10.48550/arxiv.2602.22633","title":"Tackling Privacy Heterogeneity in Differentially Private Federated Learning","display_name":"Tackling Privacy Heterogeneity in Differentially Private Federated Learning","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7131816323","doi":"https://doi.org/10.48550/arxiv.2602.22633"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.22633","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":"article","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/A5101020101","display_name":"Ruichen Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Ruichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127251964","display_name":"Ying-Jun Angela Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ying-Jun Angela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126226530","display_name":"Jianwei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jianwei","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22358318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9907000064849854,"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":0.9907000064849854,"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":0.0012000000569969416,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6776000261306763},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.6617000102996826},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.616599977016449},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.5771999955177307},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5257999897003174},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.43709999322891235},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3912999927997589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8145999908447266},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6776000261306763},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6617000102996826},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.616599977016449},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.5771999955177307},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38089999556541443},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3346000015735626},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3215999901294708},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C102938260","wikidata":"https://www.wikidata.org/wiki/Q1999831","display_name":"Privacy policy","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C193934123","wikidata":"https://www.wikidata.org/wiki/Q7246028","display_name":"Privacy by Design","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.22633","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.2602.22633","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22633","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":"pmh:doi:10.48550/arxiv.2602.22633","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/16","display_name":"Peace, Justice and strong institutions","score":0.4287128150463104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Differentially":[0],"private":[1],"federated":[2,189],"learning":[3,11],"(DP-FL)":[4],"enables":[5],"clients":[6,29,69],"to":[7,79,141,156,166],"collaboratively":[8],"train":[9],"machine":[10],"models":[12],"while":[13],"preserving":[14],"the":[15,89,111,176],"privacy":[16,33,45,50,81,114,171,180],"of":[17,93,113,178],"their":[18],"local":[19],"data.":[20],"However,":[21],"most":[22],"existing":[23,167],"DP-FL":[24],"approaches":[25],"assume":[26],"that":[27,37,109,136,151],"all":[28],"share":[30],"a":[31,53,101,106,125,132,157],"uniform":[32],"budget,":[34],"an":[35],"assumption":[36],"does":[38],"not":[39],"hold":[40],"in":[41,97,160],"real-world":[42],"scenarios":[43],"where":[44],"requirements":[46],"vary":[47],"widely.":[48],"This":[49],"heterogeneity":[51,115,181],"poses":[52],"significant":[54],"challenge:":[55],"conventional":[56],"client":[57,95,127,183],"selection":[58,96,128,139,184],"strategies,":[59],"which":[60],"typically":[61],"rely":[62],"on":[63,116,120,147,163],"data":[64],"quantity,":[65],"cannot":[66],"distinguish":[67],"between":[68],"providing":[70],"high-quality":[71],"updates":[72],"and":[73,187],"those":[74],"introducing":[75],"substantial":[76],"noise":[77],"due":[78],"strict":[80],"constraints.":[82],"To":[83],"address":[84],"this":[85,121],"gap,":[86],"we":[87,123],"present":[88],"first":[90],"systematic":[91],"study":[92],"privacy-aware":[94,126],"DP-FL.":[98],"We":[99],"establish":[100],"theoretical":[102],"foundation":[103],"by":[104],"deriving":[105],"convergence":[107],"analysis":[108],"quantifies":[110],"impact":[112],"training":[117,143],"error.":[118,144],"Building":[119],"analysis,":[122],"propose":[124],"strategy,":[129],"formulated":[130],"as":[131],"convex":[133],"optimization":[134],"problem,":[135],"adaptively":[137],"adjusts":[138],"probabilities":[140],"minimize":[142],"Extensive":[145],"experiments":[146],"benchmark":[148],"datasets":[149],"demonstrate":[150],"our":[152],"approach":[153],"achieves":[154],"up":[155],"10%":[158],"improvement":[159],"test":[161],"accuracy":[162],"CIFAR-10":[164],"compared":[165],"baselines":[168],"under":[169],"heterogeneous":[170],"budgets.":[172],"These":[173],"results":[174],"highlight":[175],"importance":[177],"incorporating":[179],"into":[182],"for":[185],"practical":[186],"effective":[188],"learning.":[190]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-02-28T00:00:00"}