{"id":"W4409494265","doi":"10.1109/tccn.2025.3561292","title":"pFedDHPO: A Differentiable Approach for Personalized Hyperparameter Optimization in Federated Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Cognitive Communications and Networking","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; Fundamental Research Funds for the Central Universities; National Central University","keywords":"Hyperparameter; Computer science; Differentiable function; Artificial intelligence; Machine learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003157264,0.0001522608,0.0001959061,0.000314066,0.0008391613,0.0002612394,0.002997097,0.0001166768,0.000003280952],"category_scores_gemma":[0.0002291391,0.0001620739,0.0000535864,0.0008501567,0.0001597135,0.0002961469,0.0005330603,0.0004643791,6.48167e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006128468,"about_ca_system_score_gemma":0.00004095471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002065565,"about_ca_topic_score_gemma":0.00002454441,"domain_scores_codex":[0.9988254,0.0002168382,0.0002423864,0.0003870166,0.00008343082,0.0002449833],"domain_scores_gemma":[0.9971637,0.001096072,0.00007506577,0.00150976,0.0001280211,0.00002734514],"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":[0.0001951732,0.001068892,0.0006523679,0.00012869,0.0003142575,0.00000113916,0.0005079501,0.03205922,0.0002357633,0.002251166,0.0008277894,0.9617576],"study_design_scores_gemma":[0.0008854493,0.00005100554,0.00002577521,0.0002636223,0.00002988205,0.000002010306,0.0001896576,0.9952209,0.0002838661,0.002246056,0.0006471753,0.0001546231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006942954,0.0009850543,0.9947997,0.001481663,0.00009633283,0.0005145509,0.00001026253,0.0002644008,0.001153762],"genre_scores_gemma":[0.6912079,0.002238828,0.3057971,0.0001433233,0.000005310857,0.000411323,0.00003551794,0.000009625782,0.0001511229],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9631616,"threshold_uncertainty_score":0.6609182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05388359086966833,"score_gpt":0.3004697731211985,"score_spread":0.2465861822515302,"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."}}