{"id":"W4315629593","doi":"10.1109/globecom48099.2022.10001721","title":"FedRL: Improving the Performance of Federated Learning with Non-IID Data","year":2022,"lang":"en","type":"article","venue":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Federated learning; Convergence (economics); Machine learning; Artificial intelligence; Data aggregator; Homogeneous; Training set; Data mining; 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":[0.006134666,0.00118087,0.001564832,0.0007331057,0.000852535,0.001450757,0.002433139,0.001561839,0.00109197],"category_scores_gemma":[0.01926961,0.0004032278,0.0005989515,0.0007896391,0.001352273,0.003320411,0.002632568,0.002454563,0.0004727046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001221608,"about_ca_system_score_gemma":0.002091593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005894007,"about_ca_topic_score_gemma":0.004571192,"domain_scores_codex":[0.9980847,0.0006090892,0.0001375093,0.0004614457,0.0004482678,0.0002589076],"domain_scores_gemma":[0.993614,0.002957712,0.0004772636,0.001699952,0.001003668,0.0002474826],"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":[0.0005300289,0.0003741866,0.003540413,0.00006518132,0.0001104943,0.0001498521,0.0001360423,0.8246927,0.002494744,0.005657053,0.003398504,0.1588509],"study_design_scores_gemma":[0.00001949019,0.00004022478,0.00009706314,0.000004102587,0.000004294827,0.00001977353,0.000008491852,0.9965572,0.0008636701,0.00222558,0.000155609,0.000004428945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09914438,0.0006320688,0.8923484,0.0005971637,0.0001503026,0.0001170109,0.0001122919,0.004927343,0.001970968],"genre_scores_gemma":[0.8715833,0.0001379072,0.1262319,0.000289294,0.00004626727,0.00008629368,0.0001972283,0.0001416693,0.001286211],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006134666,"threshold_uncertainty_score":0.03244358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05647577360395995,"score_gpt":0.2909231474283444,"score_spread":0.2344473738243845,"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."}}