{"id":"W4388666109","doi":"10.1109/twc.2023.3330967","title":"Channel-Aware Joint AoI and Diversity Optimization for Client Scheduling in Federated Learning With Non-IID Datasets","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Wireless Communications","topic":"Age of Information Optimization","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Computer science; Scalability; Scheduling (production processes); Markov decision process; Independent and identically distributed random variables; Telecommunications link; Convergence (economics); Distributed computing; Job shop scheduling; Channel (broadcasting); Artificial intelligence; Markov process; Mathematical optimization; Schedule; Computer network; Random variable; Database","routes":{"ca_aff":true,"ca_fund":true,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003607724,0.0001553165,0.0001662622,0.0004742306,0.001767316,0.0001991202,0.0006181942,0.00008258362,0.000004560501],"category_scores_gemma":[0.00001193147,0.000163995,0.00003520798,0.001110333,0.00007988903,0.001163094,0.00006739494,0.0003018226,0.00001322825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001052328,"about_ca_system_score_gemma":0.00006814146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006812176,"about_ca_topic_score_gemma":0.0001898215,"domain_scores_codex":[0.9988914,0.00009573,0.0003135565,0.000268521,0.0002022626,0.0002285714],"domain_scores_gemma":[0.998656,0.0001986646,0.0001566558,0.0007212423,0.0001877701,0.00007965937],"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":[0.00001526444,0.00007784715,0.00002150245,0.00002064159,0.0000165262,6.841128e-7,0.001442008,0.9937503,0.00001516606,0.0001293601,0.00002997252,0.00448072],"study_design_scores_gemma":[0.0008014696,0.00009008266,0.0002162885,0.0001011757,0.0000115554,0.000004160096,0.0005841315,0.9974483,0.0005022799,0.00001774961,0.00003766461,0.0001851017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008384044,0.000007298363,0.9891298,0.001414467,0.00007783785,0.0005651774,0.00006037028,0.0003143314,0.00004667243],"genre_scores_gemma":[0.9394345,0.0003765064,0.05947813,0.00009512942,0.000004776273,0.000174598,0.0003822669,0.00001584109,0.00003825911],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9310504,"threshold_uncertainty_score":0.9995322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03477498577339587,"score_gpt":0.2594133022138545,"score_spread":0.2246383164404586,"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."}}