{"id":"W3170790803","doi":"10.1109/tccn.2021.3084406","title":"Fast-Convergent Federated Learning With Adaptive Weighting","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Cognitive Communications and Networking","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":208,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Node (physics); Weighting; Convergence (economics); Orchestration; Artificial intelligence; Theoretical computer science","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002287937,0.0001877569,0.0001819733,0.0001207062,0.001489961,0.0002640182,0.003191476,0.00008833697,0.00001453909],"category_scores_gemma":[0.0001193022,0.0001847125,0.00004443053,0.0008751856,0.0002060197,0.0004057109,0.001036804,0.000802671,0.00001189535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005392225,"about_ca_system_score_gemma":0.00009298181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002081612,"about_ca_topic_score_gemma":0.0001655708,"domain_scores_codex":[0.9985374,0.0003076506,0.0002199237,0.0004633597,0.0001754741,0.0002961746],"domain_scores_gemma":[0.9961242,0.0008922063,0.0001176148,0.002474458,0.0003208522,0.00007064884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003332684,0.0001979432,0.0001714322,0.000009935533,0.0002094871,0.00002713471,0.0003389122,0.0002723885,0.0003183906,0.0004901859,0.0002365482,0.9976943],"study_design_scores_gemma":[0.0008329701,0.0002822512,0.0001146435,0.0008290249,0.0000731861,0.000108582,0.001426837,0.9782075,0.01159559,0.003077196,0.00296598,0.0004862393],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002509722,0.001255931,0.9892082,0.004011321,0.0001683558,0.0001535732,0.000009487655,0.0004680375,0.002215326],"genre_scores_gemma":[0.8952205,0.004288032,0.1000514,0.0002448377,0.00001894234,0.00007236841,0.00001331176,0.00001748697,0.0000731844],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9972081,"threshold_uncertainty_score":0.99981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04948721404327679,"score_gpt":0.2725010338649894,"score_spread":0.2230138198217126,"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."}}