{"id":"W4388675115","doi":"10.1109/allerton58177.2023.10313432","title":"Near-optimal Differentially Private Client Selection in Federated Settings","year":2023,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Mitacs","keywords":"Differential privacy; Computer science; Task (project management); Probabilistic logic; Selection (genetic algorithm); Selection algorithm; Computation; Federated learning; Client-side; Server; Differential (mechanical device); Private information retrieval; Distributed computing; Computer network; Data mining; Machine learning; Algorithm; Artificial intelligence; Computer security","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004619433,0.0008831191,0.001850793,0.0007420512,0.001154034,0.001928284,0.002954429,0.001978845,0.001963948],"category_scores_gemma":[0.01383498,0.0004771879,0.0007842649,0.001592056,0.00133229,0.003044072,0.002734964,0.001713943,0.0007146898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001887946,"about_ca_system_score_gemma":0.002569867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001236477,"about_ca_topic_score_gemma":0.001146203,"domain_scores_codex":[0.9952968,0.002074569,0.0001894917,0.0007766191,0.0009926572,0.0006699783],"domain_scores_gemma":[0.9913113,0.004898018,0.0006530548,0.001866993,0.0008365577,0.0004341608],"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":[0.001826429,0.000472996,0.003445846,0.0001446864,0.0001363541,0.0003312413,0.0004166279,0.7274187,0.01455917,0.08282924,0.005589932,0.1628287],"study_design_scores_gemma":[0.00005558753,0.00006569399,0.0001530991,0.000005435713,0.00001081357,0.00009414781,0.00002924278,0.9646103,0.002698534,0.03169636,0.0005690961,0.00001172343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03142302,0.0001470399,0.9658983,0.0003036582,0.00002570348,0.0001144792,0.00009147234,0.000681478,0.001314852],"genre_scores_gemma":[0.7775579,0.0001431624,0.2189489,0.0002041586,0.00004650503,0.0002564393,0.0002211683,0.00008615402,0.002535635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004619433,"threshold_uncertainty_score":0.02443022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02100806965862406,"score_gpt":0.2656149646267127,"score_spread":0.2446068949680887,"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."}}