{"id":"W3178661111","doi":"10.1109/tpds.2021.3096076","title":"Decentralized Edge Intelligence: A Dynamic Resource Allocation Framework for Hierarchical Federated Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Parallel and Distributed Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":290,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Ministry of Education, India; National Research Foundation Singapore; National Natural Science Foundation of China; Nanyang Technological University; Singapore University of Technology and Design; Ministry of Education - Singapore; National Research Foundation","keywords":"Computer science; Server; Distributed computing; Bottleneck; Resource allocation; Incentive; Edge device; Raw data; Enhanced Data Rates for GSM Evolution; Artificial intelligence; Computer network; Cloud computing","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":[0.002414951,0.0006347319,0.0009949764,0.0005332002,0.0007968746,0.001841215,0.002881221,0.001331402,0.003635298],"category_scores_gemma":[0.003140848,0.0003922799,0.00074236,0.0008885188,0.001319324,0.002234381,0.002410695,0.001472016,0.0004750775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001708174,"about_ca_system_score_gemma":0.002382722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005068809,"about_ca_topic_score_gemma":0.005181888,"domain_scores_codex":[0.9987265,0.0004711346,0.00005202119,0.0002513611,0.0002489057,0.0002500213],"domain_scores_gemma":[0.9990859,0.0003806406,0.00009859855,0.0001484472,0.0001556812,0.0001306756],"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":[0.0001249311,0.00009306755,0.0003692443,0.00007320871,0.00004245611,0.0001531098,0.0001284464,0.7827828,0.00130133,0.1753848,0.003032283,0.03651441],"study_design_scores_gemma":[0.00001217773,0.00001732865,0.00003492675,0.000005445811,0.000004461219,0.0000170567,0.00001247993,0.9633199,0.000176945,0.03518689,0.001207447,0.000004980714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006329959,0.0002235347,0.9887663,0.0003082067,0.00003428058,0.00006694461,0.00006904266,0.0003581403,0.0038435],"genre_scores_gemma":[0.6733015,0.0004263583,0.3182094,0.0003143033,0.00007767187,0.0003175076,0.0002040626,0.0001136201,0.007035492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005068809,"threshold_uncertainty_score":0.01277167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02898207518150444,"score_gpt":0.2913225440989919,"score_spread":0.2623404689174875,"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."}}