{"id":"W4212984905","doi":"10.1109/tits.2022.3149860","title":"Clustered Vehicular Federated Learning: Process and Optimization","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Bottleneck; Scheduling (production processes); Independent and identically distributed random variables; Distributed computing; Vehicular ad hoc network; Salient; Process (computing); Enhanced Data Rates for GSM Evolution; Aggregate (composite); Machine learning; Artificial intelligence; Computer network; Wireless ad hoc network; Wireless; Engineering; Telecommunications","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003789258,0.0002189037,0.000224578,0.0003479442,0.0008433983,0.0002316057,0.002960228,0.00009971266,0.00006073386],"category_scores_gemma":[0.00006208204,0.0002398512,0.00006537489,0.0008786065,0.00004983688,0.0005338751,0.00003911736,0.0005425635,0.00001018655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001343765,"about_ca_system_score_gemma":0.00008208964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007549328,"about_ca_topic_score_gemma":0.00001545822,"domain_scores_codex":[0.9977973,0.0001989813,0.0005257737,0.000623649,0.0005906698,0.0002636217],"domain_scores_gemma":[0.9982852,0.00009647641,0.0001889489,0.00120157,0.0001451909,0.00008266767],"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":[0.00002953645,0.0001088698,0.00005049396,0.00005989147,0.00004635229,0.00001414853,0.0005718777,0.9953665,0.0001300299,0.0001589389,0.0002833228,0.003180054],"study_design_scores_gemma":[0.0003174729,0.0002316421,0.00002411431,0.00003711509,0.00002278879,0.00002917971,0.00119463,0.9902225,0.006201867,0.0002683041,0.001176442,0.0002739866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01461605,0.0001467316,0.9812992,0.001256022,0.0009580612,0.0006000411,0.00005987528,0.00101422,0.00004986647],"genre_scores_gemma":[0.9926507,0.00009444285,0.006494216,0.00006566724,0.00001071613,0.0004487207,0.00007063647,0.00002695164,0.0001379377],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9780347,"threshold_uncertainty_score":0.9780847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02708650245758665,"score_gpt":0.2628556969118116,"score_spread":0.235769194454225,"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."}}