{"id":"W4417038151","doi":"10.1049/cit2.70090","title":"Multi‐Objective Optimisation Framework for Heterogeneous Federated Learning","year":2025,"lang":"en","type":"article","venue":"CAAI Transactions on Intelligence Technology","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"National Research Foundation of Korea","keywords":"Federated learning; Selection (genetic algorithm); Key (lock); Computation; Subnetwork; Sizing; Scheme (mathematics); Heterogeneous network","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.0002381058,0.0002779731,0.0002827616,0.001125984,0.0006852454,0.0001477368,0.008903536,0.0007282056,0.00002395839],"category_scores_gemma":[0.00685141,0.0003000942,0.0001166753,0.00214306,0.000302364,0.0002866579,0.001068715,0.001080621,0.00005135746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002917295,"about_ca_system_score_gemma":0.000117872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001218549,"about_ca_topic_score_gemma":0.00001594032,"domain_scores_codex":[0.9979779,0.00005962006,0.0004016327,0.0009086972,0.0001440958,0.0005080855],"domain_scores_gemma":[0.9957411,0.0005921535,0.0001285216,0.003238969,0.0002583318,0.00004095498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005740883,0.0003185955,0.00005031241,0.00004615459,0.0001835148,0.00001286164,0.0001252671,0.02793531,0.002235685,0.05601599,0.000594308,0.9124246],"study_design_scores_gemma":[0.0001034532,0.0002167177,0.000004833348,0.00008410696,0.00001330049,0.00001514827,0.0002122364,0.3612472,0.2715702,0.3656948,0.0006372872,0.0002007821],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001137702,0.0001875472,0.9785795,0.01498529,0.000709464,0.0006465164,0.00001392246,0.003634707,0.0001053478],"genre_scores_gemma":[0.4688417,0.0001113831,0.5303858,0.0001410083,0.000005255026,0.0003739084,0.000003768778,0.00001356693,0.0001236159],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9122238,"threshold_uncertainty_score":0.9999451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03560905398971009,"score_gpt":0.3241529245288061,"score_spread":0.288543870539096,"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."}}