{"id":"W4387303325","doi":"10.1109/jsac.2023.3310046","title":"Digital Twin Enhanced Federated Reinforcement Learning With Lightweight Knowledge Distillation in Mobile Networks","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":178,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"Japan Society for the Promotion of Science; National Natural Science Foundation of China","keywords":"Computer science; Reinforcement learning; Cloud computing; Distributed computing; Edge device; Edge computing; Enhanced Data Rates for GSM Evolution; Artificial intelligence; Operating system","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":[0.0008903324,0.000550466,0.0007818297,0.0001981226,0.0003796579,0.0007780474,0.00116335,0.00068816,0.001001949],"category_scores_gemma":[0.001799667,0.0002523046,0.0003172586,0.0002373459,0.0007694916,0.0009054806,0.001209863,0.001112152,0.0001788978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006956115,"about_ca_system_score_gemma":0.001099062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00583887,"about_ca_topic_score_gemma":0.004547996,"domain_scores_codex":[0.9995837,0.0001013537,0.0000204358,0.0001125817,0.00008225581,0.00009980194],"domain_scores_gemma":[0.9993948,0.0002580693,0.00007996125,0.0000808371,0.0001286125,0.00005772287],"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":[0.0001455006,0.00006935142,0.0005351945,0.00003960636,0.00002294467,0.00008695282,0.0000495071,0.9520511,0.002672657,0.006003085,0.0005562863,0.03776772],"study_design_scores_gemma":[0.000004381773,0.00001418993,0.00002736339,0.000001271994,0.000002077876,0.000003979378,0.000002257299,0.9985337,0.0003079087,0.001024774,0.0000764343,0.000001535734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06240419,0.0003317825,0.9342049,0.0002292853,0.00005864274,0.00003842179,0.00003693469,0.0005798787,0.002115914],"genre_scores_gemma":[0.9664618,0.00006755308,0.0321542,0.00007669059,0.00001281503,0.00003940651,0.00003110624,0.00001507163,0.001141448],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00583887,"threshold_uncertainty_score":0.01160979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02766455617979272,"score_gpt":0.29365498016363,"score_spread":0.2659904239838373,"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."}}