{"id":"W4413177599","doi":"10.1016/j.patcog.2025.112281","title":"Enhancing federated learning through exploring filter-aware relationships and personalizing local structures","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Sichuan Province Science and Technology Support Program; Sichuan University; National Natural Science Foundation of China","keywords":"Computer science; Filter (signal processing); Artificial intelligence; Human–computer interaction; Computer vision","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":[],"consensus_categories":[],"category_scores_codex":[0.0003193845,0.0001603146,0.000144339,0.0001563417,0.0005866547,0.0003434147,0.001759593,0.0001165041,0.00002135608],"category_scores_gemma":[0.003373665,0.0001705897,0.00002998932,0.0003685085,0.00005941894,0.001335013,0.007519156,0.0005752417,0.00002136256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008927201,"about_ca_system_score_gemma":0.00002934603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001164813,"about_ca_topic_score_gemma":0.00007486051,"domain_scores_codex":[0.9986287,0.0001903858,0.0002404467,0.0005047596,0.0001682788,0.000267398],"domain_scores_gemma":[0.9986346,0.0003384432,0.00009541435,0.0008191328,0.00008305348,0.00002935886],"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":[0.000007379848,0.00001919427,0.01293216,0.0001822045,0.00005270824,0.0000233032,0.001134797,0.00003103266,0.001572888,0.0002364026,0.001826234,0.9819817],"study_design_scores_gemma":[0.00106192,0.0001186701,0.02119526,0.002063486,0.00005328781,0.00007765096,0.006410196,0.3773305,0.1144426,0.4755797,0.0006995875,0.0009670986],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1935758,0.0001696303,0.8027357,0.002236388,0.0002467791,0.0001039007,0.000006785925,0.0006380947,0.0002868961],"genre_scores_gemma":[0.9494218,0.000094133,0.0501123,0.0001994684,0.00003247488,0.00004805194,0.00006680281,0.00001073857,0.00001428656],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9810146,"threshold_uncertainty_score":0.9372091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1109865748576561,"score_gpt":0.2886748619540611,"score_spread":0.1776882870964051,"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."}}