{"id":"W3045590453","doi":"10.1109/icc40277.2020.9148987","title":"GGS: General Gradient Sparsification for Federated Learning in Edge Computing","year":2020,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Normalization (sociology); Overhead (engineering); Gradient descent; Federated learning; Edge device; Enhanced Data Rates for GSM Evolution; Process (computing); Algorithm; Distributed computing; Artificial intelligence; Artificial neural network","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":[0.001624913,0.001185653,0.001156562,0.000557056,0.000442478,0.001037595,0.001647278,0.001037948,0.002321776],"category_scores_gemma":[0.004274243,0.0004064597,0.0008188804,0.0007800296,0.001181239,0.001930722,0.001987024,0.002005953,0.000877674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007823607,"about_ca_system_score_gemma":0.001499639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003237993,"about_ca_topic_score_gemma":0.003633182,"domain_scores_codex":[0.9991344,0.0002649717,0.00007163544,0.0002005884,0.0002348103,0.00009373465],"domain_scores_gemma":[0.9990926,0.0002379762,0.00008076349,0.0003391552,0.0001893599,0.00006012575],"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":[0.0003118394,0.0001411599,0.001570917,0.0001781186,0.0001075211,0.000203506,0.0001407796,0.6959865,0.006770542,0.05796703,0.009230457,0.2273916],"study_design_scores_gemma":[0.00001029361,0.00002356097,0.00008455868,0.0000069458,0.000004496391,0.00003087144,0.000007663075,0.9849823,0.001625356,0.01215,0.001068254,0.000005758984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006243882,0.0002099788,0.9908386,0.0001821385,0.00004630513,0.00005521835,0.00008666891,0.001362886,0.0009742223],"genre_scores_gemma":[0.4265327,0.0005461588,0.5663903,0.000452557,0.0001317061,0.0003295708,0.0007579027,0.0005417106,0.004317339],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003237993,"threshold_uncertainty_score":0.00859344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07068235908234331,"score_gpt":0.2888670132584494,"score_spread":0.2181846541761061,"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."}}