{"id":"W4385627407","doi":"10.1109/tmc.2023.3303017","title":"DetFed: Dynamic Resource Scheduling for Deterministic Federated Learning Over Time-Sensitive Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Windsor; Memorial University of Newfoundland","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Jitter; Reinforcement learning; Scheduling (production processes); Network packet; Distributed computing; Markov decision process; Queueing theory; Transmission delay; Packet loss; Server; Computer network; Real-time computing; Markov process; Artificial intelligence; Mathematical optimization","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0008185407,0.0003588816,0.0003851719,0.0003769851,0.002001011,0.0004592591,0.0004746933,0.0001817886,0.000003092744],"category_scores_gemma":[0.00003454018,0.0003986437,0.0002480524,0.001227081,0.00005847747,0.000209264,0.00002827142,0.0006997288,0.0001533501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001948323,"about_ca_system_score_gemma":0.0001122502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008410825,"about_ca_topic_score_gemma":0.000002168443,"domain_scores_codex":[0.9972393,0.000210259,0.0005146299,0.000841121,0.0002871662,0.0009075251],"domain_scores_gemma":[0.9973773,0.001775399,0.0001962735,0.0003657477,0.0001247563,0.0001605349],"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":[0.00002089969,0.00003671347,0.000006601584,0.00002039962,0.00003686419,0.00002391154,0.0006297493,0.8150173,0.0008161502,0.000006352389,0.0001126214,0.1832725],"study_design_scores_gemma":[0.0005712708,0.000261998,0.00009011202,0.0001949751,0.00002499548,0.00003114389,0.00006999909,0.9961573,0.001287309,0.00003922858,0.0008406492,0.0004309604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1367433,0.00002098374,0.8574579,0.00005540661,0.003637205,0.0004989825,9.914123e-7,0.001463379,0.0001218581],"genre_scores_gemma":[0.984525,0.000004321582,0.01393336,0.0001651664,0.0005961833,0.00004074203,0.00001393708,0.00007017308,0.0006511743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8477817,"threshold_uncertainty_score":0.9998465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01156234265538069,"score_gpt":0.2615333743360205,"score_spread":0.2499710316806398,"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."}}