{"id":"W3110379447","doi":"10.48550/arxiv.2012.00661","title":"Fast-Convergent Federated Learning with Adaptive Weighting","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Orchestration; Node (physics); MNIST database; Weighting; Convergence (economics); Enhanced Data Rates for GSM Evolution; Function (biology); Artificial intelligence; Data mining; Deep learning","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0002279222,0.0004947179,0.0004678166,0.0002636327,0.0003844317,0.000302986,0.02229292,0.0003945215,0.00003394554],"category_scores_gemma":[0.00163938,0.0005236341,0.0001333658,0.001149076,0.0001852406,0.0006376279,0.1424717,0.001984117,0.0001598325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003569701,"about_ca_system_score_gemma":0.0003352186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001621054,"about_ca_topic_score_gemma":0.00003456351,"domain_scores_codex":[0.9967573,0.0002209379,0.0002390596,0.002024083,0.0001890681,0.0005696031],"domain_scores_gemma":[0.9941154,0.0001489505,0.0004467707,0.004870036,0.0002187001,0.0002001127],"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":[0.0008448968,0.0005794877,0.02536996,0.0007547268,0.003050722,0.01597501,0.001736681,0.5607185,0.001066183,0.2875128,0.082061,0.02033005],"study_design_scores_gemma":[0.0004084902,0.0001648732,0.0002286616,0.0001745167,0.00004792739,0.00000875299,0.0002106912,0.9208967,0.0008841697,0.0757246,0.000619907,0.000630702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05854843,0.00004492063,0.9320495,0.003229837,0.0003619002,0.000334698,0.00001535755,0.002441324,0.002974017],"genre_scores_gemma":[0.9429339,0.0001082806,0.05640124,0.0001250443,0.00004943886,0.000001994884,0.00003382171,0.00003539204,0.0003109037],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8843855,"threshold_uncertainty_score":0.9997215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08287029827922732,"score_gpt":0.194891386868446,"score_spread":0.1120210885892187,"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."}}