{"id":"W4391382811","doi":"10.1109/camsap58249.2023.10403421","title":"Multi-Model Federated Learning Optimization Based on Multi-Agent Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Concordia University","funders":"","keywords":"Reinforcement learning; Computer science; Markov decision process; Mathematical optimization; Q-learning; Optimization problem; Artificial intelligence; Scheme (mathematics); Resource allocation; Decision problem; Base station; Markov process; Algorithm; Computer network","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":[0.002263845,0.001155448,0.001907649,0.0005033896,0.000662976,0.00101296,0.001713885,0.001536796,0.001205007],"category_scores_gemma":[0.004302619,0.0004835748,0.0007284734,0.000532155,0.001133333,0.001308209,0.00153871,0.001573207,0.0001910491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113975,"about_ca_system_score_gemma":0.001606505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005983579,"about_ca_topic_score_gemma":0.004077077,"domain_scores_codex":[0.999018,0.0003725226,0.00004171951,0.0002193564,0.0001727821,0.0001757032],"domain_scores_gemma":[0.997788,0.001229679,0.0002812167,0.0002104824,0.0003472874,0.0001433313],"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":[0.00003597201,0.00004539096,0.000305032,0.00001585492,0.00002515863,0.00003329521,0.00001702085,0.9872623,0.0002532593,0.002198339,0.0002513117,0.009557049],"study_design_scores_gemma":[0.00000503873,0.00001372922,0.00001932189,0.000001095879,0.0000021195,0.000003703532,0.000002161323,0.9988335,0.00007085254,0.001010283,0.00003700409,0.000001314474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0251617,0.0001546056,0.9729534,0.0002161389,0.00003333325,0.0000428207,0.00002644089,0.0003257085,0.001085815],"genre_scores_gemma":[0.9277052,0.00007621158,0.07057598,0.000153939,0.0000254918,0.0001033145,0.00006966163,0.00003543756,0.001254664],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005983579,"threshold_uncertainty_score":0.01197249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0660352790647838,"score_gpt":0.3000029513614536,"score_spread":0.2339676722966698,"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."}}