{"id":"W4402741153","doi":"10.1016/j.jpdc.2024.104990","title":"Robust and Scalable Federated Learning Framework for Client Data Heterogeneity Based on Optimal Clustering","year":2024,"lang":"en","type":"article","venue":"Journal of Parallel and Distributed Computing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Brock University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Scalability; Cluster analysis; Federated learning; Biclustering; Data mining; Distributed computing; Artificial intelligence; Database; Fuzzy clustering; Canopy clustering 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":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001191867,0.0001868155,0.0002916442,0.0001372483,0.0003747062,0.00105955,0.004136286,0.0001293207,0.00000115697],"category_scores_gemma":[0.005243253,0.0001592581,0.00005370799,0.0003077291,0.0000610657,0.000522756,0.01464882,0.000636219,8.176045e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005800982,"about_ca_system_score_gemma":0.00007579565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003446478,"about_ca_topic_score_gemma":0.000001078634,"domain_scores_codex":[0.9983549,0.0000818534,0.0004609901,0.0004972721,0.0002533956,0.0003515859],"domain_scores_gemma":[0.9975055,0.0008534385,0.0002414159,0.001177353,0.0001003608,0.0001218776],"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":[0.0001763077,0.0001382857,0.003580894,0.0003735354,0.0001902979,0.000288081,0.00006834519,0.8897634,0.0001192227,0.002142265,0.01860747,0.08455187],"study_design_scores_gemma":[0.0004252377,0.0002831315,0.0005652169,0.0005847165,0.00001992936,0.0001477372,0.00003830579,0.9922615,0.00006763587,0.004523133,0.0009144989,0.0001689792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0476564,0.0009307964,0.9459872,0.004709729,0.0003437242,0.0001072065,0.00005628388,0.0001981155,0.00001049673],"genre_scores_gemma":[0.5229208,0.00003504465,0.4768738,0.00005392982,0.00007168953,7.639698e-7,0.00003538063,0.00000771294,8.523498e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4752644,"threshold_uncertainty_score":0.9999775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07238156506958848,"score_gpt":0.3162229305768396,"score_spread":0.2438413655072511,"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."}}