{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0002175077,0.0001977665,0.0001866103,0.0001346355,0.00119251,0.0003020058,0.02733868,0.0001162749,0.00003201437],"category_scores_gemma":[0.0004824182,0.0001943084,0.00005867539,0.001300333,0.0002668315,0.0008281294,0.001492875,0.00122502,0.0001765026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008646504,"about_ca_system_score_gemma":0.00009784722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006769928,"about_ca_topic_score_gemma":0.0001054954,"domain_scores_codex":[0.9984421,0.0003408962,0.0002949534,0.0004013484,0.0002631447,0.0002575698],"domain_scores_gemma":[0.9867573,0.0004792737,0.0001417036,0.01233027,0.0001728887,0.0001185456],"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":[0.0003662079,0.004264281,0.0006106627,0.0001874038,0.001348552,0.00003660587,0.008210651,0.2285135,0.01850236,0.02934605,0.1494208,0.5591928],"study_design_scores_gemma":[0.0005544265,0.0002617282,0.00006031025,0.00006978383,0.00002906803,0.00001745968,0.0002239426,0.9773706,0.009596115,0.002474526,0.008967413,0.0003746389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006029184,0.0001302751,0.8529345,0.1415955,0.00003940404,0.0002328572,0.00001324726,0.001855424,0.00259593],"genre_scores_gemma":[0.6718155,0.0003984822,0.3270722,0.0005349991,0.000004322171,0.00009424509,0.00001932416,0.00001917558,0.00004176305],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7488571,"threshold_uncertainty_score":0.9779239,"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."}}