{"id":"W3010012151","doi":"10.1109/tcomm.2020.2979149","title":"Robust Federated Learning With Noisy Communication","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"National Key Research and Development Program of China","keywords":"Computer science; Maxima and minima; Noise (video); Convergence (economics); Mathematical optimization; Node (physics); Process (computing); Function (biology); Convex function; Wireless; Convexity; Artificial intelligence; Regular polygon; Mathematics; Telecommunications; Engineering","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":[0.002969546,0.001207142,0.00183916,0.0005031576,0.0006392252,0.001332367,0.002248497,0.001505543,0.001141142],"category_scores_gemma":[0.008834469,0.0005637388,0.0007131209,0.0007388999,0.001451404,0.00242144,0.002038891,0.001968291,0.0004501505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008755865,"about_ca_system_score_gemma":0.00156065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001794447,"about_ca_topic_score_gemma":0.001531227,"domain_scores_codex":[0.9975357,0.0007106775,0.0001450412,0.0007331251,0.0005582792,0.0003171117],"domain_scores_gemma":[0.9957727,0.001835759,0.0005030031,0.0009048053,0.0008363884,0.0001474155],"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":[0.0002838603,0.000119066,0.0007663524,0.00006801566,0.00005994541,0.0001061716,0.00007457119,0.9173254,0.003100683,0.01210605,0.0009148838,0.06507502],"study_design_scores_gemma":[0.000008167125,0.00004378121,0.0000539382,0.000004445639,0.000005079161,0.00002151611,0.000005045098,0.9954695,0.001198423,0.003035011,0.0001493952,0.000005779491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01084928,0.00008742028,0.9879677,0.00008825259,0.00002149682,0.00001811852,0.00001997258,0.0003427336,0.0006049441],"genre_scores_gemma":[0.8848063,0.0001247196,0.1128424,0.000166836,0.00004183819,0.000114339,0.00008911846,0.00005592016,0.001758495],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002969546,"threshold_uncertainty_score":0.01570463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08482952423078478,"score_gpt":0.2744377171142667,"score_spread":0.1896081928834819,"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."}}