{"id":"W4401725036","doi":"10.1109/tai.2024.3446759","title":"Differentially Private and Heterogeneity-Robust Federated Learning With Theoretical Guarantee","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"National Natural Science Foundation of China","keywords":"Computer science; Federated learning; Econometrics; Artificial intelligence; Economics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002856251,0.0002690885,0.0002042735,0.0002550207,0.0003811861,0.0009770872,0.003614394,0.0001447845,0.00006505241],"category_scores_gemma":[0.000246285,0.0002193781,0.00006461393,0.000736499,0.0005343047,0.0005013834,0.0003199418,0.0008006824,0.0001352336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005782607,"about_ca_system_score_gemma":0.0000589219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001556877,"about_ca_topic_score_gemma":0.00005361333,"domain_scores_codex":[0.9979683,0.0001233205,0.0003342144,0.0008257683,0.0003379125,0.0004104516],"domain_scores_gemma":[0.9978918,0.0003236367,0.00004060133,0.001604684,0.00006176584,0.00007752766],"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":[0.0001351136,0.0002475569,0.000009139943,0.00007034639,0.0001609913,0.0001911171,0.0002996027,0.01126583,0.01381694,0.1793387,0.0001505794,0.7943141],"study_design_scores_gemma":[0.00001885353,0.0002328311,0.000004408507,0.0001095322,0.00001623434,0.00005150705,0.00002772282,0.594372,0.3178213,0.08706705,0.00006899439,0.0002096362],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1039426,0.0000761783,0.8895992,0.004245515,0.0005077051,0.000193398,0.000009652167,0.00134966,0.00007607893],"genre_scores_gemma":[0.9599254,0.0001450192,0.03975713,0.00006758155,0.00002477302,0.00003275905,0.000001705918,0.00002638721,0.00001922808],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8559828,"threshold_uncertainty_score":0.9422074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04268208421082591,"score_gpt":0.2843459582456893,"score_spread":0.2416638740348633,"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."}}