{"id":"W4410294847","doi":"10.1109/tmc.2025.3569407","title":"Efficient Model Training in Edge Networks With Hierarchical Split Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Training (meteorology); Enhanced Data Rates for GSM Evolution; Artificial intelligence; Machine learning","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":[0.0005522709,0.0002220064,0.0002702012,0.0003818587,0.0004929662,0.0001404501,0.0004772461,0.00009776522,0.000004381098],"category_scores_gemma":[0.000007658002,0.0002076846,0.00008897315,0.001046629,0.00005747246,0.00006019794,0.00001155612,0.001115358,0.000007281714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009469991,"about_ca_system_score_gemma":0.0001554851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002962625,"about_ca_topic_score_gemma":0.00001468308,"domain_scores_codex":[0.9981639,0.0001657093,0.000326265,0.0005958571,0.0002252043,0.0005230511],"domain_scores_gemma":[0.9990727,0.000371993,0.00006731503,0.0003554687,0.00004067388,0.00009184023],"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":[0.00001586849,0.00008237761,0.00003703119,0.00001055141,0.00001075027,0.000007243132,0.0021693,0.7256782,0.00001562084,0.0007987248,0.000003007721,0.2711713],"study_design_scores_gemma":[0.0005867071,0.0001375398,0.0001458079,0.0002308818,0.000007797271,0.00001061043,0.0001311166,0.9982575,0.00006317044,0.00006149046,0.0001612971,0.0002060366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.144794,0.0000382748,0.8525717,0.0001853806,0.0003096949,0.000196763,2.938209e-7,0.0003522506,0.001551577],"genre_scores_gemma":[0.9675007,0.000002933783,0.031816,0.0002051737,0.0000328298,0.00003125309,6.198894e-7,0.00001645027,0.0003940749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8227066,"threshold_uncertainty_score":0.8469132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01048774381927405,"score_gpt":0.2536253834284963,"score_spread":0.2431376396092222,"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."}}