{"id":"W3047304572","doi":"10.1109/infocom41043.2020.9155494","title":"Optimizing Federated Learning on Non-IID Data with Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":958,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Computer science; Upload; Reinforcement learning; Independent and identically distributed random variables; Artificial intelligence; Machine learning; Mobile device; Convergence (economics); Software deployment; Federated learning; Distributed computing; Data modeling; Database; World Wide Web","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":[0.004571631,0.001527397,0.002123794,0.0005168653,0.0006246941,0.001421831,0.002466389,0.001856617,0.001573812],"category_scores_gemma":[0.01421276,0.0007299668,0.000726886,0.000593369,0.002206,0.002126409,0.002327411,0.002804103,0.0004252057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001527303,"about_ca_system_score_gemma":0.002035805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007253494,"about_ca_topic_score_gemma":0.006402917,"domain_scores_codex":[0.9983059,0.0006635563,0.00009093162,0.0004172906,0.0002555855,0.0002666997],"domain_scores_gemma":[0.9910608,0.006103529,0.0005860922,0.0008931223,0.0009488697,0.0004076879],"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":[0.0001380429,0.00010068,0.0008852906,0.00002935703,0.00003035552,0.00005025393,0.00002975318,0.9811245,0.0003691555,0.002282945,0.0006026266,0.01435694],"study_design_scores_gemma":[0.00001153954,0.00001526273,0.00004692948,0.000002480747,0.000002109676,0.000004124667,0.00000409926,0.997888,0.0001277274,0.001857587,0.00003814139,0.00000193402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09763737,0.0004316485,0.8976805,0.0007184111,0.00009934492,0.000115054,0.0001274469,0.001416962,0.001773335],"genre_scores_gemma":[0.9359953,0.00008754739,0.06159655,0.0002649823,0.00003760816,0.0001452305,0.0001873406,0.00008017329,0.001605235],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007253494,"threshold_uncertainty_score":0.02417737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05745084960832399,"score_gpt":0.2763946947713953,"score_spread":0.2189438451630714,"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."}}