{"id":"W4312602762","doi":"10.1109/jstsp.2022.3223498","title":"Wireless Federated Learning With Hybrid Local and Centralized Training: A Latency Minimization Design","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Info-communications Media Development Authority; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Research Foundation Singapore","keywords":"Computer science; Upload; Computer network; Wireless; Feature (linguistics); Training (meteorology); Server; Local area network; Latency (audio); Distributed computing; Operating system; Telecommunications","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":[],"consensus_categories":[],"category_scores_codex":[0.0007101957,0.0001655495,0.0003010937,0.0003361638,0.0004025656,0.0002719206,0.003035687,0.00005742175,0.000008664909],"category_scores_gemma":[0.0007597139,0.0001508742,0.00002046659,0.001310125,0.00009079058,0.0008222343,0.00159497,0.001059322,1.228024e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001949706,"about_ca_system_score_gemma":0.0006378917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005960435,"about_ca_topic_score_gemma":0.000002106284,"domain_scores_codex":[0.9979966,0.000337346,0.0005003547,0.0002910221,0.0005148127,0.0003598371],"domain_scores_gemma":[0.9986499,0.0001400512,0.0005274024,0.0002977617,0.0003153555,0.0000695269],"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":[0.0007153754,0.000374709,0.004935535,0.0001631289,0.0001214772,0.001646207,0.004301137,0.110627,0.01697269,0.0001456715,0.002316104,0.857681],"study_design_scores_gemma":[0.001346139,0.0006784748,0.0002985874,0.0001934032,0.00001550604,0.001254817,0.0004394038,0.9765697,0.01070529,0.008111354,0.0001446334,0.0002427382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.186774,0.0003132815,0.8109413,0.00168045,0.00007063949,0.00009718051,6.127305e-7,0.0001014583,0.00002107114],"genre_scores_gemma":[0.872255,0.00003873981,0.1275856,0.00005303825,0.00003486168,0.000005366233,0.000001779482,0.00001447022,0.00001106095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8659427,"threshold_uncertainty_score":0.615247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03354321227861804,"score_gpt":0.2523201774147574,"score_spread":0.2187769651361393,"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."}}