{"id":"W4386280917","doi":"10.1109/tmc.2023.3309633","title":"RingSFL: An Adaptive Split Federated Learning Towards Taming Client Heterogeneity","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Convergence (economics); Scheme (mathematics); Distributed computing; Data modeling; Raw data; Information privacy; Benchmark (surveying); Computer network; Computer security; Database","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":[0.004107682,0.0007830209,0.001231926,0.0006078548,0.0008477034,0.001079191,0.003330804,0.001550841,0.001254566],"category_scores_gemma":[0.00956602,0.0004168832,0.0006917976,0.0006826373,0.001546622,0.003694546,0.004040905,0.001863263,0.0004712552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009515584,"about_ca_system_score_gemma":0.001688589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002282822,"about_ca_topic_score_gemma":0.002555956,"domain_scores_codex":[0.997344,0.0009496073,0.0001338347,0.0006884927,0.0005503547,0.0003337071],"domain_scores_gemma":[0.9948071,0.001962754,0.0003761063,0.001884949,0.0007031337,0.0002660383],"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":[0.001041917,0.0004498696,0.003917073,0.0001015046,0.000170414,0.0002296583,0.0003088673,0.6410261,0.01065233,0.01592937,0.004485703,0.3216872],"study_design_scores_gemma":[0.00002375993,0.00007780402,0.0001138031,0.000004375927,0.000008651579,0.00004384735,0.00001778446,0.9917389,0.002003005,0.005565671,0.0003937704,0.000008668047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.028766,0.000160861,0.9686687,0.0001789837,0.0000315903,0.00004761807,0.00004220369,0.001500052,0.000603983],"genre_scores_gemma":[0.8496545,0.00009100225,0.1471048,0.0004786392,0.00004374838,0.0001181013,0.0002144186,0.0001168731,0.002177896],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004107682,"threshold_uncertainty_score":0.02172375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0481440027074141,"score_gpt":0.3056492883687118,"score_spread":0.2575052856612977,"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."}}