{"id":"W4402216761","doi":"10.1109/tccn.2024.3454273","title":"Accelerating Federated Learning for Edge Intelligence Using Conjugated Central Acceleration With Inexact Global Line Search","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Cognitive Communications and Networking","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Acceleration; Enhanced Data Rates for GSM Evolution; Line (geometry); Artificial intelligence; Machine learning","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003655896,0.0002229547,0.0001869444,0.0001591884,0.001552349,0.001131304,0.00282504,0.0001197516,0.000005307576],"category_scores_gemma":[0.0001415268,0.000213252,0.00005052127,0.001207703,0.0002116589,0.0008514165,0.000554702,0.0007128998,0.000002882784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000160229,"about_ca_system_score_gemma":0.0001586143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006468091,"about_ca_topic_score_gemma":0.0001626381,"domain_scores_codex":[0.998381,0.0002032883,0.0003153025,0.0005141443,0.0001710344,0.0004151897],"domain_scores_gemma":[0.9971522,0.001084411,0.00007369891,0.001311969,0.000301067,0.00007662873],"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":[0.0000746074,0.0001228789,0.0001130114,0.00006340574,0.0001876429,0.000006416378,0.0003758717,0.01058605,0.0006388224,0.0006278782,0.00005776248,0.9871457],"study_design_scores_gemma":[0.0002292808,0.000247334,0.00001989008,0.0008095698,0.00004683029,0.00003573108,0.000293474,0.9924601,0.004240196,0.00117961,0.000195375,0.0002426483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009139015,0.001461373,0.9859551,0.00170891,0.0002663399,0.0005465535,0.00003760378,0.0007133838,0.0001716805],"genre_scores_gemma":[0.9058483,0.001625705,0.09223246,0.00008052336,0.00005434363,0.00008391217,0.00004507647,0.00002116495,0.000008476361],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.986903,"threshold_uncertainty_score":0.9999056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1468672489350608,"score_gpt":0.3599130017835388,"score_spread":0.213045752848478,"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."}}