{"id":"W7117134956","doi":"10.1109/tmc.2025.3647655","title":"KAFL-HD: Knowledge Alignment in Asynchronous Federated Learning With Heterogeneous Data","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China","keywords":"Federated learning; Asynchronous communication; Convergence (economics); Training (meteorology); Order (exchange); Quality (philosophy); Recommender system; Training set","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":[0.003388687,0.000943429,0.001435328,0.0009331427,0.0009877551,0.001752142,0.003193681,0.001377424,0.001739682],"category_scores_gemma":[0.01020679,0.0003982208,0.0005999354,0.001259906,0.0009272255,0.004634887,0.003268358,0.001831264,0.000513017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00131667,"about_ca_system_score_gemma":0.002462547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006137135,"about_ca_topic_score_gemma":0.005262851,"domain_scores_codex":[0.9979395,0.000488337,0.0001567253,0.0007093342,0.0004253242,0.0002807695],"domain_scores_gemma":[0.9961797,0.001357765,0.0003597425,0.001117439,0.0007443592,0.000241077],"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":[0.0007268869,0.0005922429,0.004266833,0.0002526679,0.0001483316,0.0002372328,0.0005007352,0.4221146,0.005319015,0.01492237,0.005833441,0.5450857],"study_design_scores_gemma":[0.0000416162,0.00006546879,0.000320895,0.00001037839,0.00001798564,0.0000592933,0.00004819941,0.9845255,0.001881238,0.01208747,0.0009282377,0.00001364692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0263821,0.0003085146,0.9694605,0.000230948,0.00005666418,0.00008039776,0.0001029567,0.002201937,0.001175963],"genre_scores_gemma":[0.7872086,0.0001886284,0.2089146,0.0004355426,0.00008897148,0.0002044396,0.0004181728,0.0001274899,0.002413652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006137135,"threshold_uncertainty_score":0.01792133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03051056994780319,"score_gpt":0.2988475692155677,"score_spread":0.2683369992677644,"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."}}