{"id":"W4416323579","doi":"10.1109/tdsc.2025.3634446","title":"Fed-EHP: Efficient and Heterogeneous Privacy-Preserving Personalized Federated Learning","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hyperion Technologies (Canada)","funders":"Key Research and Development Program of Zhejiang Province; National Natural Science Foundation of China","keywords":"Federated learning; Personalization; Cluster analysis; Inference; Limiting; Information privacy; Heterogeneous network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00116465,0.0008998037,0.0009378843,0.0008179483,0.004084074,0.002188793,0.007908853,0.0006401518,0.00006938071],"category_scores_gemma":[0.001551858,0.0009791278,0.0002238327,0.001703387,0.0004735939,0.0005257245,0.00493552,0.002378294,0.00001860814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002547065,"about_ca_system_score_gemma":0.000291836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002280583,"about_ca_topic_score_gemma":0.00005652377,"domain_scores_codex":[0.9940135,0.0006101839,0.001021178,0.002279981,0.0006778705,0.001397326],"domain_scores_gemma":[0.9944096,0.001110312,0.0003658986,0.003527253,0.0002819474,0.0003050069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006183599,0.001150031,0.0005109978,0.001875889,0.001520113,0.0006374205,0.004683589,0.2457698,0.005005808,0.0008051506,0.004062806,0.73336],"study_design_scores_gemma":[0.001749132,0.0003496115,0.00004826775,0.001265896,0.0001493094,0.0002695354,0.0004109065,0.978319,0.01320352,0.001802929,0.001607955,0.0008238904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2573792,0.003935338,0.7307131,0.004827812,0.001314124,0.0005926886,0.00002625128,0.0008859631,0.00032548],"genre_scores_gemma":[0.9704616,0.0009168938,0.02770518,0.0003314479,0.00005220629,0.00001897384,0.000006295144,0.00006094163,0.0004464692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7325492,"threshold_uncertainty_score":0.9999233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01833486361537659,"score_gpt":0.2648299778323469,"score_spread":0.2464951142169703,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}