{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0002988342,0.0001046507,0.0001327126,0.00007812838,0.0001382159,0.0001895565,0.007300966,0.00006695213,0.000003680256],"category_scores_gemma":[0.00710434,0.0001039971,0.00002894752,0.000544702,0.00002478961,0.0003142689,0.01551202,0.0002047914,0.00002117851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006275882,"about_ca_system_score_gemma":0.00003457005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003024066,"about_ca_topic_score_gemma":0.00001008035,"domain_scores_codex":[0.998807,0.00004821318,0.0002409499,0.0004887469,0.0001220124,0.0002930554],"domain_scores_gemma":[0.9985269,0.0001149896,0.00008199484,0.001173108,0.00005070736,0.00005232509],"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":[0.00004261413,0.0001984856,0.01921335,0.0001469668,0.00004895094,0.00002966156,0.001771822,0.008597163,0.02411356,0.0826519,0.4122283,0.4509572],"study_design_scores_gemma":[0.0002778882,0.00006533461,0.001327394,0.00001064395,9.888189e-7,0.000001644025,0.00004431275,0.9807311,0.006243704,0.007577194,0.003589921,0.0001299157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06249941,0.00003613756,0.8882518,0.04720867,0.0001284007,0.0002341646,0.00000126698,0.001149843,0.0004902554],"genre_scores_gemma":[0.5914477,0.000004896604,0.407978,0.0004782883,0.00003640141,0.000009585979,0.00001595541,0.000006225407,0.00002299561],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9721339,"threshold_uncertainty_score":0.99807,"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."}}