{"id":"W4394804896","doi":"10.1109/tnse.2024.3386623","title":"Privacy-Preserving Heterogeneous Personalized Federated Learning With Knowledge","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Information privacy; Federated learning; Privacy protection; Internet privacy; Artificial intelligence","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":[0.005395478,0.0009564155,0.001842786,0.000790749,0.001661174,0.002566283,0.003575972,0.002002779,0.00140463],"category_scores_gemma":[0.01344835,0.0006023581,0.001506577,0.001497676,0.001560756,0.007264369,0.006800529,0.002649476,0.00049101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001678267,"about_ca_system_score_gemma":0.002362393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002221548,"about_ca_topic_score_gemma":0.002220273,"domain_scores_codex":[0.9936801,0.001881424,0.000386763,0.001988665,0.001339549,0.0007234737],"domain_scores_gemma":[0.9906343,0.002221503,0.0005895458,0.005530322,0.0007022749,0.0003220429],"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":[0.001403968,0.0006009312,0.007748981,0.000232839,0.0003297678,0.0008590975,0.00115293,0.5375453,0.009414236,0.1176147,0.007260613,0.3158368],"study_design_scores_gemma":[0.00003001451,0.00006390028,0.0002995738,0.00001098011,0.00003025335,0.000154052,0.00007965232,0.9214858,0.003897584,0.07284628,0.001080833,0.00002109638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03600641,0.0001457715,0.9609159,0.0003814715,0.00002572577,0.00007474475,0.0001662708,0.0011575,0.001126241],"genre_scores_gemma":[0.8925698,0.0001093403,0.1040839,0.0003210538,0.00004289201,0.0001445171,0.0004447277,0.00008925032,0.002194602],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005395478,"threshold_uncertainty_score":0.02853435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01640289378817495,"score_gpt":0.2402213432571476,"score_spread":0.2238184494689726,"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."}}