{"id":"W4380607150","doi":"10.1109/jiot.2023.3285868","title":"Federated Learning Over Wireless Networks: Challenges and Solutions","year":2023,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Wireless network; Wireless; Implementation; Computer network; Cloud computing; Overhead (engineering); Edge device; Enhanced Data Rates for GSM Evolution; Distributed computing; Mobile device; Key (lock); Edge computing; Computer security; Telecommunications; World Wide Web","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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001076752,0.0001351545,0.0002046266,0.0002566379,0.0001817451,0.0003063288,0.006584316,0.0001268577,0.000008282179],"category_scores_gemma":[0.002464097,0.0001238568,0.00005760793,0.0002791696,0.0001141907,0.001127464,0.01608874,0.0008484364,0.00001222425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004720776,"about_ca_system_score_gemma":0.00002935355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002830252,"about_ca_topic_score_gemma":0.000005339287,"domain_scores_codex":[0.9986209,0.0001036109,0.0003218637,0.0002753965,0.0002887707,0.0003894435],"domain_scores_gemma":[0.9985461,0.0002108006,0.0002815649,0.0007812369,0.0001032285,0.00007710712],"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":[0.0000360358,0.00009841661,0.001292484,0.00009970642,0.0003630061,0.0003509988,0.003588383,0.001181483,0.005539607,0.006299692,0.3890609,0.5920893],"study_design_scores_gemma":[0.0002346247,0.0001060985,0.001243638,0.0002638635,0.000006247223,0.000287504,0.0001346123,0.9654202,0.001162674,0.03004898,0.0009409144,0.0001505876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.306785,0.003197296,0.667778,0.01842509,0.00191736,0.00008665596,0.000001003507,0.001120001,0.0006896805],"genre_scores_gemma":[0.9850617,0.004653728,0.009961702,0.00007965601,0.00008502734,0.000002487434,9.843612e-7,0.00001404994,0.0001406684],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9642388,"threshold_uncertainty_score":0.9987906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04958844083348783,"score_gpt":0.2771914533004669,"score_spread":0.2276030124669791,"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."}}