{"id":"W4406321257","doi":"10.1109/tmlcn.2025.3528901","title":"Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Machine Learning in Communications and Networking","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Convergence (economics); Internet privacy; Computer science; Information privacy; Computer security; Business; Economics; Economic growth","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009794538,0.0002470526,0.000326249,0.0006575744,0.0009449056,0.0002444522,0.00773291,0.0001883399,0.00001357182],"category_scores_gemma":[0.0003524754,0.0002733819,0.00006537764,0.002091431,0.0002222564,0.0003892209,0.001271713,0.002140579,0.000003727124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001602829,"about_ca_system_score_gemma":0.00008370742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002942704,"about_ca_topic_score_gemma":0.0007924975,"domain_scores_codex":[0.9975917,0.0007826235,0.0004941563,0.0005400024,0.0001765107,0.0004150441],"domain_scores_gemma":[0.9955397,0.001130789,0.0001321906,0.003118981,0.00003081689,0.00004758226],"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":[0.00005726313,0.0003323946,0.02563605,0.0000466807,0.00006917554,0.00001421981,0.001144409,0.02912559,0.0002742015,0.001651813,0.0003449797,0.9413033],"study_design_scores_gemma":[0.0007902389,0.00005490376,0.001330112,0.0003727995,0.000009677098,0.000008157565,0.0001689643,0.9760006,0.0001060928,0.003683913,0.01722597,0.0002485802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01564944,0.00538278,0.9497507,0.0266862,0.0004134296,0.0003131666,0.000002761902,0.0008118456,0.0009897286],"genre_scores_gemma":[0.9622129,0.01090017,0.0264252,0.000183198,0.000009127061,0.00006522611,0.00001143548,0.00001790889,0.0001748053],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.946875,"threshold_uncertainty_score":0.9999718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03145894419834756,"score_gpt":0.2944939386433342,"score_spread":0.2630349944449867,"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."}}