{"id":"W4404056961","doi":"10.1109/tnnls.2024.3487873","title":"Tailored Federated Learning With Adaptive Central Acceleration on Diversified Global Models","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Acceleration; Computer science; Distributed computing; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002257479,0.0002808018,0.0002375494,0.0001230565,0.0009569889,0.001220427,0.001561588,0.0001827579,0.000003647651],"category_scores_gemma":[0.00004862378,0.0002311519,0.00005894253,0.0006859797,0.00007279147,0.0009798224,0.0001359285,0.001328556,0.000007185842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001603983,"about_ca_system_score_gemma":0.00003408323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001870398,"about_ca_topic_score_gemma":0.0000232695,"domain_scores_codex":[0.9978962,0.000330514,0.0002362644,0.0007264251,0.0003340146,0.0004765751],"domain_scores_gemma":[0.9987963,0.0002342532,0.00008341244,0.0007196156,0.00005901308,0.0001074112],"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":[0.00009917826,0.00002285829,0.00003144719,0.0000196674,0.00006927312,0.0000508761,0.00009311385,0.9690404,0.0000181927,0.0006597645,0.0007607981,0.02913442],"study_design_scores_gemma":[0.000297393,0.0007296422,0.00005513477,0.0002576543,0.00002198931,0.00005868931,0.0001979954,0.9977601,0.0000394849,0.0001756449,0.0001483267,0.000257981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02281865,0.0003231353,0.9723222,0.001122313,0.001192652,0.0003070603,0.000006100772,0.001686385,0.0002215101],"genre_scores_gemma":[0.9982166,0.00009006329,0.001339272,0.00004018574,0.00008089643,0.00003403538,0.00000833784,0.00002163404,0.0001690058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9753979,"threshold_uncertainty_score":0.9998164,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03238164456541935,"score_gpt":0.2385064684992302,"score_spread":0.2061248239338108,"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."}}