{"id":"W4391853798","doi":"10.1109/tmc.2024.3365951","title":"CPPer-FL: Clustered Parallel Training for Efficient Personalized Federated Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Training (meteorology); Computer architecture; Multimedia; Distributed computing; Computer network; Artificial intelligence","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":[0.001455326,0.0009717057,0.001117669,0.0007223441,0.0008950253,0.0009047088,0.003040278,0.001301226,0.003369031],"category_scores_gemma":[0.003657945,0.0004508084,0.0006593465,0.0008087676,0.0006607821,0.002479823,0.002099784,0.001742439,0.001089446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001018373,"about_ca_system_score_gemma":0.001746449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006309932,"about_ca_topic_score_gemma":0.007130659,"domain_scores_codex":[0.9988822,0.0002155975,0.00005923884,0.0003628781,0.0002845368,0.0001955662],"domain_scores_gemma":[0.9986544,0.0003172645,0.00009748089,0.000531505,0.0003056024,0.00009379286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004003568,0.0004397659,0.002106461,0.0001169698,0.00009360393,0.0001571058,0.0001570348,0.4878222,0.007215057,0.007962801,0.008617128,0.4849116],"study_design_scores_gemma":[0.0000169249,0.00003982854,0.0001545696,0.000003426433,0.000006405689,0.00004827621,0.00001722469,0.9938102,0.001815117,0.003251841,0.0008296727,0.000006501185],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01149722,0.0001077251,0.9829729,0.0001261038,0.00003446014,0.00007394027,0.0000553898,0.003834786,0.001297528],"genre_scores_gemma":[0.5451008,0.0001170734,0.4481615,0.0004500496,0.00005117306,0.0003066301,0.0006867626,0.000355784,0.004770213],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006309932,"threshold_uncertainty_score":0.01254642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04878786099221449,"score_gpt":0.3069871642057065,"score_spread":0.258199303213492,"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."}}