{"id":"W4416582540","doi":"10.1109/tmc.2025.3636225","title":"A Radical Heavy-Ball Method for Gradient Acceleration in Communication-Efficient Mobile Federated Learning","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Dalian Science and Technology Innovation Fund; Natural Science Foundation of Liaoning Province","keywords":"Stochastic gradient descent; Convergence (economics); Gradient descent; Acceleration; Momentum (technical analysis); Process (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":[0.001460702,0.001074678,0.001381208,0.0005999597,0.0006931921,0.0008999171,0.00184518,0.001078547,0.002253071],"category_scores_gemma":[0.004423102,0.000475444,0.0006199329,0.0005883034,0.0009157625,0.001288908,0.001747707,0.001641537,0.0007882693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008021998,"about_ca_system_score_gemma":0.001862178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006336573,"about_ca_topic_score_gemma":0.004876875,"domain_scores_codex":[0.9992822,0.0002132499,0.00004066849,0.0001421978,0.0002178611,0.0001038853],"domain_scores_gemma":[0.9989575,0.0003990737,0.0000858974,0.000150473,0.0003154922,0.00009166301],"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":[0.0002136953,0.00009780858,0.001148987,0.000114361,0.00005349281,0.000146199,0.0001585761,0.802612,0.004067328,0.02431753,0.004124705,0.1629453],"study_design_scores_gemma":[0.000009206015,0.00002061486,0.00003132044,0.000003706504,0.000002339665,0.00001184871,0.00000535593,0.9968171,0.0003826875,0.002245755,0.0004664872,0.000003709728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007712559,0.0001848991,0.9901329,0.0001493703,0.00006897279,0.00003551231,0.00001924188,0.0006291089,0.001067397],"genre_scores_gemma":[0.522184,0.0002988935,0.4704181,0.0003527776,0.0001107882,0.0002616383,0.000196038,0.0003347532,0.005843006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006336573,"threshold_uncertainty_score":0.01259935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03208207163068903,"score_gpt":0.3350631530160988,"score_spread":0.3029810813854097,"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."}}