{"id":"W4205093761","doi":"10.1109/tmc.2021.3136611","title":"Joint Client Selection and Bandwidth Allocation Algorithm for Federated Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Research Foundation","keywords":"Computer science; Markov decision process; Curse of dimensionality; Reinforcement learning; Scheduling (production processes); Mathematical optimization; Wireless; Algorithm; Bandwidth (computing); Distributed computing; Markov process; Computer network; Artificial intelligence; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004208471,0.0001702233,0.0001880565,0.0001540946,0.0008660652,0.0003177358,0.001202078,0.0001203913,0.000006608527],"category_scores_gemma":[0.0003301426,0.0001902335,0.00006721815,0.0005878191,0.00003503359,0.0003189152,0.0002778822,0.0004038009,0.000006463703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000130814,"about_ca_system_score_gemma":0.00008294128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001484324,"about_ca_topic_score_gemma":0.00001263837,"domain_scores_codex":[0.9984237,0.0001168415,0.0003004153,0.0006520864,0.000189841,0.0003171272],"domain_scores_gemma":[0.9984099,0.0002620945,0.0001096835,0.0009286371,0.0002289648,0.00006073208],"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":[0.000003010968,0.0001043204,0.000009429507,0.00002248436,0.00003330788,0.000003302179,0.00009224477,0.03900659,0.005954185,0.00004949621,0.0005180115,0.9542036],"study_design_scores_gemma":[0.0003590139,0.0001805161,0.00003881835,0.00005354207,0.00001062146,0.00005174318,0.00007442129,0.8727616,0.1245328,0.001161384,0.0006024381,0.0001731559],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01850537,0.00008367669,0.9785257,0.0009706429,0.000612379,0.0003413037,0.000005517709,0.0009248426,0.00003059312],"genre_scores_gemma":[0.5654618,0.00004724685,0.4342719,0.00006432294,0.00003107815,0.0000564075,0.000007851589,0.00001397751,0.00004540543],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9540305,"threshold_uncertainty_score":0.7757498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02474850513147081,"score_gpt":0.2705951086697189,"score_spread":0.2458466035382481,"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."}}