{"id":"W4402716324","doi":"10.1109/cvpr52733.2024.00582","title":"Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bridging (networking); Computer science; Federated learning; Distributed computing; Computer architecture; Human–computer interaction; Computer 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0007895954,0.0001239397,0.0001675531,0.0001951533,0.0001696034,0.0005026033,0.004466031,0.00006582803,0.00001695859],"category_scores_gemma":[0.002359357,0.00008872581,0.0000356855,0.0006938286,0.00012034,0.0004749275,0.0199485,0.0003891821,0.000002609672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003726565,"about_ca_system_score_gemma":0.00005936975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002740715,"about_ca_topic_score_gemma":0.00001791326,"domain_scores_codex":[0.9986974,0.0001428605,0.0002439166,0.0004134737,0.0002331759,0.0002691507],"domain_scores_gemma":[0.9986677,0.000149023,0.00005426805,0.00107305,0.00003320243,0.00002281321],"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":[0.00005618408,0.00008707324,0.008238363,0.0005293238,0.0002867981,0.0006046486,0.00349209,0.002786601,0.3539838,0.1076237,0.017794,0.5045174],"study_design_scores_gemma":[0.0002392705,0.00001855083,0.0005676487,0.0001477735,0.000004796309,0.00004532914,0.0001220428,0.9816924,0.004411777,0.01225224,0.0003834085,0.0001147097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.420657,0.001459718,0.5617579,0.01455099,0.0001683778,0.0001600659,9.48963e-7,0.0008145225,0.000430512],"genre_scores_gemma":[0.9248648,0.0000912144,0.07483774,0.00005583301,0.00002011782,0.000009153541,0.000002593219,0.00001052824,0.000108034],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9789059,"threshold_uncertainty_score":0.987978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02388362220174342,"score_gpt":0.2689185206581773,"score_spread":0.2450348984564339,"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."}}