{"id":"W4315783855","doi":"10.1109/jsac.2023.3235443","title":"Federated Deep Reinforcement Learning for Recommendation-Enabled Edge Caching in Mobile Edge-Cloud Computing Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Communications","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Key Research and Development Program of China; Chongqing Research Program of Basic Research and Frontier Technology; Fundamental Research Funds for the Key Research Program of Chongqing Science and Technology Commission; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Server; Cloud computing; Edge computing; Enhanced Data Rates for GSM Evolution; Distributed computing; Markov decision process; Mobile edge computing; Edge device; Reinforcement learning; Computer network; Base station; Recommender system; Markov process; Artificial intelligence; Machine learning; 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":[0.001030718,0.0006003764,0.001288483,0.0002711262,0.0004014916,0.0006967102,0.00143161,0.0009713938,0.001141131],"category_scores_gemma":[0.002981023,0.0003915441,0.0003908082,0.000409877,0.0005895369,0.0007636371,0.0007003582,0.001178765,0.0001821742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001333002,"about_ca_system_score_gemma":0.001472478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02570452,"about_ca_topic_score_gemma":0.02790138,"domain_scores_codex":[0.9995512,0.0001278935,0.00001981726,0.0001079788,0.00007276363,0.0001202741],"domain_scores_gemma":[0.9984905,0.0009150284,0.0001468681,0.00009369272,0.0002562024,0.00009779719],"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":[0.00007987876,0.00005961644,0.0007820416,0.00002798892,0.00002712104,0.00004676658,0.00001969922,0.9808462,0.0005521386,0.001821658,0.000533486,0.01520342],"study_design_scores_gemma":[0.000003169719,0.000007120981,0.00004070398,9.217154e-7,0.000002471237,0.000002354415,0.000001713705,0.999461,0.00006988049,0.0003805133,0.00002903547,0.000001062291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1375977,0.0009185218,0.856549,0.0005759003,0.00009640177,0.00006049688,0.0001038619,0.0008536706,0.003244288],"genre_scores_gemma":[0.9775088,0.0001099316,0.02079741,0.0001087422,0.0000187996,0.00003054047,0.00006064096,0.00002001726,0.001345241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02570452,"threshold_uncertainty_score":0.05110985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03701572615767868,"score_gpt":0.2985865757943792,"score_spread":0.2615708496367005,"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."}}