{"id":"W3082902110","doi":"10.48550/arxiv.2009.00081","title":"Federated Edge Learning : Design Issues and Challenges","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Scalability; Federated learning; Distributed learning; Scheduling (production processes); Multidisciplinary approach; Data science; Edge device; Distributed computing; Artificial intelligence; Machine learning; Key (lock); Enhanced Data Rates for GSM Evolution; Computer security; Cloud computing; Database; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01039345,0.0005756637,0.001409076,0.0005285607,0.0009829412,0.004272468,0.004100842,0.002310292,0.003250628],"category_scores_gemma":[0.02173469,0.0004802197,0.0006973908,0.001418388,0.002281304,0.007416994,0.003397475,0.003899887,0.001103853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001479538,"about_ca_system_score_gemma":0.001704711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007516175,"about_ca_topic_score_gemma":0.000959784,"domain_scores_codex":[0.9938819,0.003070408,0.0003157327,0.0007998042,0.00147305,0.0004590141],"domain_scores_gemma":[0.9867605,0.006685098,0.0004193301,0.003527693,0.002106341,0.0005009983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000477726,0.0004114427,0.001995853,0.0004975498,0.00009641502,0.0002293221,0.0002537541,0.2055984,0.003775609,0.3573239,0.009719161,0.4196208],"study_design_scores_gemma":[0.00004300892,0.0002217782,0.0002377314,0.00008834052,0.00002685978,0.0003418539,0.0001897505,0.7114573,0.005660294,0.2671492,0.01455732,0.00002660387],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006664792,0.0007849191,0.9852241,0.002770033,0.0001144021,0.0001280314,0.00006348515,0.0005977905,0.003652416],"genre_scores_gemma":[0.3924623,0.001765279,0.5973731,0.001660369,0.0002785206,0.0005821744,0.0002650689,0.0002146528,0.005398648],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01039345,"threshold_uncertainty_score":0.05496651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2233482168469003,"score_gpt":0.2266577171684384,"score_spread":0.003309500321538122,"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."}}