{"id":"https://openalex.org/W7213430384","doi":"https://doi.org/10.48550/arxiv.2609.17284","title":"Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptation","display_name":"Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptation","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213430384","doi":"https://doi.org/10.48550/arxiv.2609.17284"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.17284","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17284","pdf_url":"https://arxiv.org/pdf/2609.17284","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":null,"license_id":null,"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/2609.17284","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045092080","display_name":"Polycarpo Souza Neto","orcid":"https://orcid.org/0000-0001-5057-1942","observed_orcids":["https://orcid.org/0000-0001-5057-1942"]},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Neto, Polycarpo Souza","raw_affiliation_strings":["Universidade Federal do Cear\u00e1 , Fortaleza , CE , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal do Cear\u00e1 , Fortaleza , CE , Brazil","institution_ids":["https://openalex.org/I243754102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027243235","display_name":"Jos\u00e9 Mairton B. da Silva","orcid":"https://orcid.org/0000-0002-4503-4242","observed_orcids":["https://orcid.org/0000-0002-4503-4242"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00fanior, Jos\u00e9 Mairton Barros da Silva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061118449","display_name":"Charles C. Cavalcante","orcid":"https://orcid.org/0000-0002-4198-4064","observed_orcids":["https://orcid.org/0000-0002-4198-4064"]},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Cavalcante, Charles Casimiro","raw_affiliation_strings":["Universidade Federal do Cear\u00e1 , Fortaleza , CE , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal do Cear\u00e1 , Fortaleza , CE , Brazil","institution_ids":["https://openalex.org/I243754102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.00039999998989515007,"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/personalized-federated-learning","display_name":"personalized federated learning","score":0.9929999709129333},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.9229999780654907},{"id":"https://openalex.org/keywords/label-skew","display_name":"label skew","score":0.6700000166893005},{"id":"https://openalex.org/keywords/statistical-heterogeneity","display_name":"statistical heterogeneity","score":0.8489999771118164},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.7459999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612000107765198},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6869999766349792},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5722000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5166000127792358},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4880000054836273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4465999901294708},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.17284","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17284","pdf_url":"https://arxiv.org/pdf/2609.17284","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.17284","doi":"https://doi.org/10.48550/arxiv.2609.17284","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.17284","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.17284","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17284","pdf_url":"https://arxiv.org/pdf/2609.17284","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":null,"license_id":null,"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/W7213430384.pdf","grobid_xml":"https://content.openalex.org/works/W7213430384.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2990789643","https://openalex.org/W4378499163"],"related_works":["https://openalex.org/W7134122566","https://openalex.org/W7163103543","https://openalex.org/W7166886780","https://openalex.org/W4393186001","https://openalex.org/W4317940118","https://openalex.org/W7127404549","https://openalex.org/W4392110708","https://openalex.org/W7169815369","https://openalex.org/W4390482954","https://openalex.org/W7163362859"],"abstract_inverted_index":{"Statistical":[0],"heterogeneity":[1],"limits":[2],"federated":[3],"learning":[4],"when":[5],"a":[6,40,45],"single":[7],"global":[8,42],"classifier":[9],"cannot":[10],"represent":[11],"client-specific":[12,36],"label":[13],"distributions.":[14],"In":[15],"this":[16],"work,":[17],"we":[18],"propose":[19],"Personalized":[20],"Federated":[21],"Knowledge":[22],"Distillation":[23],"with":[24,68],"Head":[25],"Adaptation":[26],"(pFedKDH),":[27],"which":[28],"aggregates":[29],"only":[30],"the":[31,62,75,91],"shared":[32],"backbone,":[33],"keeps":[34],"persistent":[35,94],"heads,":[37],"and":[38,54,78,87,96],"uses":[39],"recalibrated":[41],"head":[43],"as":[44],"teacher":[46],"during":[47],"local":[48,98],"training.":[49],"Across":[50],"MNIST,":[51],"Fashion-MNIST,":[52],"CIFAR10,":[53],"CIFAR100":[55],"under":[56,100],"class-wise":[57],"Dirichlet":[58],"partitions,":[59],"pFedKDH":[60],"obtains":[61],"best":[63],"accuracy":[64,69],"in":[65],"most":[66],"settings,":[67],"gaps":[70],"up":[71],"to":[72],"37.67\\%":[73],"over":[74],"weakest":[76],"baseline":[77],"consistently":[79],"low":[80],"standard":[81],"deviation":[82],"across":[83],"repetitions.":[84],"Component-wise":[85],"diagnostics":[86],"convergence":[88],"results":[89],"support":[90],"role":[92],"of":[93],"heads":[95],"distillation-guided":[97],"optimization":[99],"label-skewed":[101],"data.":[102]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-17T00:00:00"}