{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001523817,0.0009071824,0.0009412317,0.001160346,0.001606549,0.001041007,0.02654062,0.0004404405,0.00004639151],"category_scores_gemma":[0.0005903756,0.0009721267,0.000137175,0.003635164,0.0004047352,0.0009003129,0.006183704,0.002779099,0.0001210848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001174292,"about_ca_system_score_gemma":0.0009833684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002168041,"about_ca_topic_score_gemma":0.0005504861,"domain_scores_codex":[0.9926671,0.0007756999,0.001368486,0.003039758,0.0006344109,0.001514573],"domain_scores_gemma":[0.985819,0.001094472,0.0004047453,0.01227597,0.0002230705,0.0001826817],"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":[0.00006901728,0.001070597,0.0001336876,0.0001948404,0.0001983087,0.0001055444,0.0003051462,0.3585388,0.0002102589,0.00001663939,0.0009286735,0.6382285],"study_design_scores_gemma":[0.00164901,0.0007274633,0.00006301051,0.002201285,0.00009011295,0.00007955997,0.0002143297,0.9788041,0.01259065,0.0004132124,0.002308491,0.0008588422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04381994,0.002804873,0.9463036,0.0009390577,0.002847618,0.001440741,0.00006785331,0.001307707,0.0004686077],"genre_scores_gemma":[0.9593496,0.00053879,0.03962557,0.00009798665,0.00006665416,0.0001025802,0.00003217387,0.00007288923,0.0001137773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9155296,"threshold_uncertainty_score":0.999996,"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."}}