{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008253654,0.0002168364,0.0002197518,0.0002897997,0.0006147869,0.0003510737,0.002248802,0.00009463565,6.414974e-7],"category_scores_gemma":[0.0001155883,0.0002146915,0.00002914136,0.002569225,0.0001485386,0.00077657,0.0002537559,0.0005418494,0.000001072963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001529838,"about_ca_system_score_gemma":0.0002796625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001190075,"about_ca_topic_score_gemma":0.00005124876,"domain_scores_codex":[0.9979771,0.00003161601,0.0002782326,0.0006634027,0.0003479097,0.0007017167],"domain_scores_gemma":[0.9988348,0.0001380453,0.0000542802,0.0007960359,0.00007998745,0.00009686007],"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":[0.00001099124,0.00002220005,0.00005536309,0.00001223297,0.000009646495,0.000005097435,0.0001196456,0.9635918,0.0006160923,0.0001182034,0.0001299745,0.03530873],"study_design_scores_gemma":[0.0002708609,0.00009300859,0.000132663,0.0001963143,0.000006696937,0.000006131802,0.00004338865,0.9957816,0.002581892,0.0006047259,0.00006984517,0.000212849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2026876,0.0001122057,0.7958394,0.0002626543,0.0003963907,0.0002058039,0.00000118679,0.0004414991,0.00005318636],"genre_scores_gemma":[0.9147552,0.00006215308,0.0850189,0.00004991958,0.0000276818,0.00006781719,9.90294e-7,0.00001034853,0.000006947245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7120676,"threshold_uncertainty_score":0.8754867,"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."}}