{"id":"W4411086466","doi":"10.1109/tnse.2025.3577910","title":"Straggler-resilient Federated Learning: Tackling Computation Heterogeneity with Layer-wise Partial Model Training in Mobile Edge Network","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Layer (electronics); Enhanced Data Rates for GSM Evolution; Computation; Training (meteorology); Computer network; Distributed computing; Artificial intelligence; Edge device; Algorithm","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":[0.002144724,0.001091981,0.001445626,0.0004627487,0.0007458953,0.0008771744,0.002435276,0.001472471,0.001105659],"category_scores_gemma":[0.005309243,0.0005883816,0.0005787138,0.0005705835,0.001015979,0.002595044,0.002178895,0.001563034,0.0002389626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001172529,"about_ca_system_score_gemma":0.001468343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009491064,"about_ca_topic_score_gemma":0.009987186,"domain_scores_codex":[0.9992208,0.000249535,0.00004085468,0.0002084148,0.0001173557,0.0001630313],"domain_scores_gemma":[0.9980987,0.001026699,0.0001173712,0.0003948437,0.0002473099,0.0001151768],"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":[0.0002248399,0.00009040959,0.0008489344,0.00002358084,0.00003856644,0.00007668331,0.00006741243,0.9446821,0.000932124,0.002463511,0.001067036,0.04948485],"study_design_scores_gemma":[0.000003414494,0.00001378625,0.00002622691,0.000001174541,0.000002439876,0.000004265774,0.000004592935,0.9984463,0.0002474203,0.001199692,0.00004939472,0.000001338301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08923611,0.0003015527,0.9066888,0.0004849668,0.00004816223,0.00004679307,0.00007884226,0.001891522,0.001223217],"genre_scores_gemma":[0.9234459,0.00008234551,0.07385766,0.0002859372,0.00002416808,0.00007228238,0.0001642735,0.00007996629,0.001987353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009491064,"threshold_uncertainty_score":0.01887161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02328220899817998,"score_gpt":0.2607421179768852,"score_spread":0.2374599089787052,"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."}}