{"id":"W4417470002","doi":"10.1109/tccn.2025.3645473","title":"Adaptive Layer-Wise Personalized Federated Deep Reinforcement Learning for Heterogeneous Edge Caching","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Cognitive Communications and Networking","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province","keywords":"Reinforcement learning; Cache; Personalization; Adaptation (eye); Latency (audio); Edge device; Enhanced Data Rates for GSM Evolution; Edge computing","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":[0.0008178381,0.000678462,0.0008458719,0.0002335343,0.0002899933,0.0004771192,0.001627247,0.0008281084,0.001239612],"category_scores_gemma":[0.00278939,0.0003301754,0.0003186232,0.0002610569,0.0006152123,0.001020641,0.0009618922,0.001325429,0.0002341836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001017371,"about_ca_system_score_gemma":0.001265696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008100873,"about_ca_topic_score_gemma":0.01116581,"domain_scores_codex":[0.9996713,0.00008063161,0.00001574768,0.00008842568,0.000061905,0.00008201196],"domain_scores_gemma":[0.999253,0.0003496565,0.00007294637,0.0000919123,0.0001678545,0.0000646737],"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":[0.0001340776,0.0001793874,0.001740942,0.00004353987,0.00003773593,0.00008027225,0.00006635847,0.9084431,0.004259598,0.003471056,0.001837142,0.07970671],"study_design_scores_gemma":[0.000004935297,0.00001319354,0.00004969455,0.000001278509,0.000002699308,0.000004878301,0.000002611336,0.9986071,0.0003065354,0.0009388123,0.00006661691,0.000001649939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07494374,0.0002967644,0.9215631,0.0002629894,0.00004690661,0.00005277072,0.00006667855,0.001050932,0.001716035],"genre_scores_gemma":[0.9450784,0.00007330771,0.05253196,0.0002176417,0.00001832322,0.00007238154,0.00009183681,0.00004428234,0.001871773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008100873,"threshold_uncertainty_score":0.01610744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06229990113681563,"score_gpt":0.2965203839878673,"score_spread":0.2342204828510517,"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."}}