{"id":"W4389042807","doi":"10.1109/isncc58260.2023.10323644","title":"Adaptive Ratio-Based-Threshold Gradient Sparsification Scheme for Federated Learning","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 Toronto","funders":"","keywords":"MNIST database; Hyperparameter; Computer science; Inference; Overhead (engineering); Algorithm; Convergence (economics); Range (aeronautics); Constant (computer programming); Rate of convergence; Independent and identically distributed random variables; Artificial intelligence; Mathematical optimization; Mathematics; Key (lock); Deep learning; Random variable; Statistics","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":[0.001861559,0.0009306277,0.00136719,0.0005339348,0.0004796283,0.0008795774,0.002345782,0.00117446,0.002242448],"category_scores_gemma":[0.006656684,0.0003523182,0.0006574845,0.0006300801,0.001098975,0.002385696,0.002055782,0.002001679,0.0007687547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007687606,"about_ca_system_score_gemma":0.001337773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001850185,"about_ca_topic_score_gemma":0.002172927,"domain_scores_codex":[0.999006,0.0002631904,0.00007989287,0.0002528853,0.0002919374,0.0001061802],"domain_scores_gemma":[0.9984676,0.000506333,0.0001737829,0.000475625,0.0002785191,0.00009812642],"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":[0.0006022984,0.0001948772,0.001776741,0.000167017,0.0001057232,0.0002259252,0.0002987461,0.5015281,0.01532104,0.04988439,0.007375314,0.4225198],"study_design_scores_gemma":[0.00002215872,0.00004156301,0.00007954625,0.000006735796,0.000006176454,0.00006287606,0.00001209426,0.986567,0.003114417,0.009330166,0.0007480719,0.00000927505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01040936,0.0001344205,0.9871804,0.0001458581,0.00004038291,0.00005842616,0.0000564746,0.001112231,0.0008624737],"genre_scores_gemma":[0.4976299,0.0001992753,0.4976238,0.0003149265,0.00008203402,0.0002242014,0.0003596545,0.00020876,0.00335749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002345782,"threshold_uncertainty_score":0.009844959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08296864288786293,"score_gpt":0.2950553509979876,"score_spread":0.2120867081101247,"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."}}