{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003174433,0.001511868,0.001857815,0.000882637,0.0006836649,0.001691455,0.002862563,0.002107065,0.003054234],"category_scores_gemma":[0.01156181,0.0008520798,0.0009540283,0.00109824,0.001374364,0.002962142,0.002916195,0.003615359,0.001143406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001050375,"about_ca_system_score_gemma":0.002149976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003329058,"about_ca_topic_score_gemma":0.00406466,"domain_scores_codex":[0.9981668,0.0007203501,0.0001077607,0.0003986826,0.0004194751,0.0001868668],"domain_scores_gemma":[0.9963581,0.002000811,0.0002361891,0.0007859018,0.0004391582,0.0001798233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002013744,0.0002136174,0.002397661,0.0001422839,0.0001145327,0.0001389235,0.0001257364,0.7583048,0.002064298,0.01260454,0.008458335,0.2152338],"study_design_scores_gemma":[0.00001522156,0.00002335991,0.00008834175,0.000009100969,0.000006083918,0.00002683004,0.00001105009,0.9888045,0.0004934036,0.009832677,0.0006827459,0.000006698013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005891901,0.000361965,0.9906754,0.0002590254,0.00003884886,0.00005555065,0.00009610913,0.001618548,0.001002481],"genre_scores_gemma":[0.5491681,0.0005572571,0.4414809,0.001159059,0.0001996117,0.0004963688,0.001023506,0.0008812994,0.005033945],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003329058,"threshold_uncertainty_score":0.01678824,"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."}}