{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008964448,0.0003422954,0.0003227019,0.0004651558,0.001224425,0.0004375859,0.007588172,0.0001926463,0.00001138747],"category_scores_gemma":[0.0003468894,0.0003729885,0.000143275,0.001740583,0.0001034842,0.0007448007,0.001321848,0.0009742656,0.0001778054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000238259,"about_ca_system_score_gemma":0.00008407328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001041893,"about_ca_topic_score_gemma":0.00002971215,"domain_scores_codex":[0.9968519,0.0002564923,0.0004699214,0.001127407,0.0005043721,0.0007899122],"domain_scores_gemma":[0.9961677,0.000291137,0.0001767327,0.003069801,0.0001346304,0.000159996],"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":[0.00001861124,0.0001702398,0.00008629198,0.00002329523,0.00006456451,0.00005925226,0.0003738736,0.3430407,0.002579317,0.00007904616,0.0004421478,0.6530627],"study_design_scores_gemma":[0.0002873442,0.0004734458,0.0004713518,0.000087109,0.000009928302,0.00002503077,0.0002610948,0.9545748,0.04239674,0.0007133115,0.0003200055,0.0003798284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.385106,0.00001496601,0.609836,0.0002443416,0.0006547529,0.0002459028,0.00000819476,0.003797776,0.00009199554],"genre_scores_gemma":[0.9096689,0.00002577828,0.09004188,0.00007051756,0.00004917989,0.00005821419,0.000008743365,0.00003996685,0.00003688922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6526828,"threshold_uncertainty_score":0.9998722,"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."}}