{"id":"W3120626278","doi":"10.1109/jiot.2021.3051611","title":"A Novel Adaptive Gradient Compression Scheme: Reducing the Communication Overhead for Distributed Deep Learning in the Internet of Things","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Carleton University","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Overhead (engineering); Deep learning; Data compression; Artificial intelligence; Node (physics); Compression ratio; Edge computing; Artificial neural network; Transmission (telecommunications); Distributed computing; Machine learning; Computer network; Computer engineering; Enhanced Data Rates for GSM Evolution; Telecommunications","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":[0.0005246451,0.0005853653,0.0005191155,0.0005967842,0.0005736079,0.0005599019,0.00120941,0.000621967,0.001677912],"category_scores_gemma":[0.001621112,0.0002086725,0.0002599075,0.0006538315,0.0005962058,0.001635624,0.001106209,0.0009628792,0.0003296002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00048524,"about_ca_system_score_gemma":0.001094923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00299917,"about_ca_topic_score_gemma":0.003949485,"domain_scores_codex":[0.9996634,0.00004294199,0.00002361815,0.00005855782,0.0001701722,0.00004135374],"domain_scores_gemma":[0.9995239,0.0001217713,0.00003939071,0.00009588329,0.0001801608,0.00003886828],"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":[0.0004645735,0.000237321,0.001834759,0.0001064519,0.00004949863,0.0002673204,0.0001544257,0.1548079,0.03344693,0.01908096,0.00884156,0.7807083],"study_design_scores_gemma":[0.00003690516,0.00008088179,0.0003527795,0.000006995634,0.00000964975,0.0001329826,0.00002210704,0.9832333,0.01100734,0.003372143,0.001732211,0.00001271973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03761445,0.0004453516,0.9577174,0.0003187678,0.0001396091,0.0001180437,0.00006632427,0.001444126,0.002135893],"genre_scores_gemma":[0.6265145,0.0003155937,0.3677032,0.0004107861,0.0001155825,0.0002007031,0.0002974896,0.0001245816,0.004317575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00299917,"threshold_uncertainty_score":0.005963385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03464347156434745,"score_gpt":0.2928884088350212,"score_spread":0.2582449372706738,"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."}}