{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003027965,0.001049779,0.001161353,0.0006242519,0.0006631975,0.00133633,0.002551429,0.001264572,0.001585971],"category_scores_gemma":[0.01228498,0.0004704698,0.0005272921,0.0006438071,0.00116249,0.002846343,0.00277308,0.00223442,0.0007010071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009215697,"about_ca_system_score_gemma":0.002200732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003947877,"about_ca_topic_score_gemma":0.004185063,"domain_scores_codex":[0.9980912,0.0005844524,0.0001201785,0.0004535845,0.0004997391,0.0002509514],"domain_scores_gemma":[0.9966868,0.001245127,0.0002504924,0.001112178,0.0004946269,0.0002108147],"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":[0.0008118889,0.0003483592,0.003973075,0.0001405008,0.0001052252,0.0001617623,0.0002101749,0.7414443,0.008967781,0.01397244,0.008148431,0.221716],"study_design_scores_gemma":[0.00003263828,0.00003200284,0.0001119674,0.000005224121,0.000005039031,0.00002588078,0.00001736612,0.9912173,0.001935337,0.006107839,0.0005030935,0.000006379745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03016617,0.0002667835,0.9592043,0.0003627485,0.00007351303,0.00007081144,0.00009842049,0.008483361,0.00127383],"genre_scores_gemma":[0.7679547,0.0001178006,0.229129,0.0003727859,0.00005267992,0.0001392694,0.0003357539,0.0003844459,0.001513532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003947877,"threshold_uncertainty_score":0.01601356,"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."}}