{"id":"W4385498284","doi":"10.1016/j.future.2023.07.033","title":"Adaptive differential privacy in vertical federated learning for mobility forecasting","year":2023,"lang":"en","type":"article","venue":"Future Generation Computer Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Differential privacy; Initialization; Federated learning; Feature (linguistics); Convergence (economics); Adaptation (eye); Information privacy; Artificial intelligence; Weighting; Machine learning; Computer security; Data mining","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006651361,0.0002348924,0.0003195861,0.0002656661,0.0003391176,0.0006296026,0.00473089,0.0002251616,0.000001772968],"category_scores_gemma":[0.001469751,0.0002219015,0.00007305591,0.0008727157,0.00002910724,0.0005539436,0.01152158,0.0003348208,0.00002067349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001569128,"about_ca_system_score_gemma":0.00007262179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002624051,"about_ca_topic_score_gemma":0.00002594225,"domain_scores_codex":[0.9975516,0.0002710709,0.0005314811,0.000819661,0.0003272961,0.0004988909],"domain_scores_gemma":[0.9975364,0.0002492723,0.0001065261,0.001859949,0.0001784483,0.00006946181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005490711,0.0001801629,0.002107399,0.0002145363,0.0001020182,0.00005756084,0.0009605064,0.04383369,0.003259729,0.01044208,0.8722538,0.06653366],"study_design_scores_gemma":[0.0005715275,0.0001439197,0.001138015,0.00004620328,0.000003188991,0.00001232696,0.00004388397,0.9920825,0.0006286891,0.0003371331,0.004759667,0.0002329333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08996605,0.00007495219,0.8858083,0.00248032,0.0197138,0.0007177311,0.00000709614,0.001219254,0.00001247273],"genre_scores_gemma":[0.8551672,0.000008450443,0.1282711,0.00005656372,0.0158448,0.000355526,0.0002307235,0.00003004273,0.00003563156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9482488,"threshold_uncertainty_score":0.9964731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07381806007811581,"score_gpt":0.276820564383731,"score_spread":0.2030025043056152,"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."}}