{"id":"W4285728720","doi":"10.1007/s10796-022-10307-z","title":"Trust-Augmented Deep Reinforcement Learning for Federated Learning Client Selection","year":2022,"lang":"en","type":"article","venue":"Information Systems Frontiers","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Université du Québec en Outaouais; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Defence Research and Development Canada","keywords":"Reinforcement learning; Computer science; Selection (genetic algorithm); Artificial intelligence; Knowledge management; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003106432,0.0009605382,0.002023351,0.000503066,0.0006889915,0.001270684,0.002449659,0.002068145,0.004277207],"category_scores_gemma":[0.01313896,0.0006091386,0.0005394215,0.0005658641,0.001383845,0.0024256,0.002363362,0.00266525,0.0008579501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00176172,"about_ca_system_score_gemma":0.002685025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006609808,"about_ca_topic_score_gemma":0.008359035,"domain_scores_codex":[0.9982761,0.0005671865,0.00007498892,0.0003625804,0.0003323039,0.000386923],"domain_scores_gemma":[0.9926373,0.004717318,0.0004228558,0.0008806124,0.0009308432,0.0004111562],"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":[0.0007650994,0.000363355,0.00221669,0.00009575293,0.00006452938,0.0001440482,0.0001193102,0.8639535,0.002308305,0.0154967,0.00491198,0.1095607],"study_design_scores_gemma":[0.000009841639,0.00001629236,0.00003998073,0.000002564693,0.00000301794,0.000007150044,0.000003627518,0.9963375,0.0002677076,0.003244987,0.00006452487,0.000002760268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06823855,0.0003911426,0.9262272,0.0007544318,0.00009733602,0.00009124204,0.0001567989,0.002003765,0.002039623],"genre_scores_gemma":[0.9584041,0.00006846582,0.03781455,0.0001666499,0.00003473023,0.0000712319,0.0001332898,0.00008300434,0.003224016],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006609808,"threshold_uncertainty_score":0.01642859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01499310569872252,"score_gpt":0.2362553509931606,"score_spread":0.221262245294438,"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."}}