{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005653673,0.001101999,0.00194187,0.0007924613,0.00109768,0.002196004,0.003634341,0.002063741,0.001482292],"category_scores_gemma":[0.02018204,0.0005226264,0.001106948,0.001649573,0.001682233,0.004308105,0.004249626,0.003127993,0.0005255901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001843144,"about_ca_system_score_gemma":0.002928846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001542253,"about_ca_topic_score_gemma":0.001207074,"domain_scores_codex":[0.9948608,0.001562274,0.0002868142,0.001226023,0.001466362,0.0005977858],"domain_scores_gemma":[0.9897382,0.005423017,0.0007966823,0.002555845,0.001146267,0.0003400429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007216936,0.0002672545,0.002016751,0.0001790059,0.0001083936,0.0002663526,0.000212127,0.7271714,0.006507873,0.07305937,0.004736968,0.1847529],"study_design_scores_gemma":[0.00002719208,0.00004691006,0.0001071109,0.000006589214,0.000009340739,0.00007925284,0.00002058215,0.971332,0.002173872,0.02573841,0.0004485118,0.00001023805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01618727,0.0002102413,0.9814574,0.0004039577,0.00002741427,0.00004875502,0.00008145851,0.000685887,0.0008976362],"genre_scores_gemma":[0.8023589,0.0002621831,0.1935116,0.0005093489,0.0001010241,0.0001966252,0.0003365747,0.0001368834,0.002586809],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005653673,"threshold_uncertainty_score":0.0298999,"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."}}