{"id":"W3024699729","doi":"10.1109/jiot.2020.2994596","title":"Toward Communication-Efficient Federated Learning in the Internet of Things With Edge Computing","year":2020,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Computer science; Overhead (engineering); Key (lock); The Internet; Gradient descent; Federated learning; Distributed computing; Edge device; Process (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":[0.001881871,0.0002008512,0.000362786,0.0001877652,0.00009633047,0.0004092123,0.02463894,0.000100145,0.00001126414],"category_scores_gemma":[0.004653835,0.0001406868,0.00008953827,0.0005962971,0.0002325371,0.0007839818,0.01344566,0.001850734,0.000006091327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008161003,"about_ca_system_score_gemma":0.00009049046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000265419,"about_ca_topic_score_gemma":0.000003145035,"domain_scores_codex":[0.9976082,0.0003691541,0.0007825163,0.0003108512,0.0006170383,0.0003122485],"domain_scores_gemma":[0.9969378,0.0004721749,0.0009940515,0.001275594,0.0002531644,0.00006728697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000818076,0.001232843,0.02624981,0.0008035351,0.001051269,0.0007487751,0.5496519,0.02610716,0.02148701,0.01129211,0.1994777,0.1610799],"study_design_scores_gemma":[0.0005551947,0.0003969485,0.0003833798,0.0007951498,0.00001089872,0.0003182797,0.001441627,0.9776573,0.01566286,0.00218375,0.0004134084,0.0001812081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3372397,0.0002179852,0.6352604,0.0261174,0.0001534361,0.000129246,5.024805e-7,0.000151515,0.0007297476],"genre_scores_gemma":[0.8911214,0.00002332781,0.1079551,0.000847001,0.00002655554,0.000001470234,0.000001430383,0.00001324118,0.00001050859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9515501,"threshold_uncertainty_score":0.9945334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04315645781601955,"score_gpt":0.2731649188066862,"score_spread":0.2300084609906666,"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."}}