{"id":"W4410614229","doi":"10.1109/tdsc.2025.3572527","title":"The Power of Bias: Optimizing Client Selection in Federated Learning With Heterogeneous Differential Privacy","year":2025,"lang":"en","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":"Simon Fraser University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Differential privacy; Selection (genetic algorithm); Information privacy; Selection bias; Computer network; Computer security; Data mining; 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":[0.009418064,0.001140326,0.002191834,0.0006435188,0.0009919466,0.002219226,0.003000104,0.001831388,0.001182214],"category_scores_gemma":[0.02765684,0.000569568,0.0008417002,0.001396705,0.002085789,0.004304938,0.003863821,0.002818871,0.0003880918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002109385,"about_ca_system_score_gemma":0.003091036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002152551,"about_ca_topic_score_gemma":0.001692576,"domain_scores_codex":[0.9931734,0.003378619,0.0002773527,0.001146394,0.001352282,0.00067188],"domain_scores_gemma":[0.9854555,0.008329934,0.0009144605,0.003139267,0.001583792,0.0005771364],"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":[0.001172788,0.000384587,0.007195391,0.0001783192,0.0001907935,0.0003208704,0.0003782143,0.7403624,0.00654558,0.05308796,0.003924723,0.1862584],"study_design_scores_gemma":[0.00002769546,0.00006094672,0.0001924264,0.000008851612,0.00001482202,0.00006190342,0.00002891348,0.9746053,0.001770312,0.02289627,0.0003227487,0.00000990672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04462422,0.0003848927,0.9525274,0.0006261719,0.00003252242,0.00007253574,0.00006180529,0.0007641376,0.0009063703],"genre_scores_gemma":[0.9015747,0.0002587385,0.09568629,0.0004178885,0.00005225537,0.0001590608,0.0001345714,0.0001148177,0.001601665],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009418064,"threshold_uncertainty_score":0.04980808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01580447681024537,"score_gpt":0.2497590021081102,"score_spread":0.2339545252978648,"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."}}