{"id":"W4319302934","doi":"10.1109/jsac.2023.3242721","title":"GIFT: Toward Accurate and Efficient Federated Learning With Gradient-Instructed Frequency Tuning","year":2023,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Communications","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Chinese University of Hong Kong; Research Grants Council, University Grants Committee; National Natural Science Foundation of China","keywords":"Computer science; Consistency (knowledge bases); Synchronization (alternating current); Metric (unit); Convergence (economics); Stability (learning theory); Distributed computing; Artificial intelligence; Real-time computing; Machine learning; Telecommunications","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":["open_science"],"category_scores_codex":[0.0007377918,0.0002316022,0.0002585788,0.0008522788,0.00105027,0.0005937824,0.01322723,0.0001225777,0.000003845934],"category_scores_gemma":[0.007048543,0.0002026685,0.0000300585,0.00464526,0.0002028911,0.0004978673,0.0084961,0.00195592,0.00002238058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002338893,"about_ca_system_score_gemma":0.0002622497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004849154,"about_ca_topic_score_gemma":0.0001090588,"domain_scores_codex":[0.9976807,0.0005305624,0.0004784784,0.0003880542,0.0003886508,0.0005335576],"domain_scores_gemma":[0.9949921,0.000713546,0.0003375456,0.003449014,0.0003687139,0.0001390748],"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":[0.0005990981,0.003542909,0.230215,0.0002855988,0.001934668,0.002707339,0.02160724,0.08741438,0.118901,0.05995468,0.08289924,0.3899388],"study_design_scores_gemma":[0.001173234,0.000340015,0.04797328,0.0004540027,0.00001556793,0.0006606176,0.0003759654,0.9336821,0.0009789909,0.01314065,0.0007132283,0.0004923875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9195922,0.0002934571,0.04946828,0.02755785,0.0002254846,0.000297848,0.000009730201,0.001721055,0.00083411],"genre_scores_gemma":[0.9270384,0.0009050714,0.07188217,0.00007199663,0.00001710892,0.00002613087,0.00002223418,0.00002315453,0.00001373227],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8462677,"threshold_uncertainty_score":0.999523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05213281843376082,"score_gpt":0.2990192269054298,"score_spread":0.246886408471669,"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."}}