{"id":"W4387211047","doi":"10.1007/978-3-031-43895-0_30","title":"FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Overfitting; Computer science; Generalization; Interpolation (computer graphics); Personalization; Code (set theory); Artificial intelligence; Machine learning; Maxima and minima; Data mining; Image (mathematics); Artificial neural 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001998834,0.00137195,0.00224978,0.001064542,0.0007475783,0.001226362,0.002914662,0.002407553,0.004564389],"category_scores_gemma":[0.00457523,0.0008524354,0.001803829,0.001177112,0.0009118887,0.003719245,0.003845719,0.003532781,0.001718703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008115682,"about_ca_system_score_gemma":0.001103153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007695785,"about_ca_topic_score_gemma":0.008744938,"domain_scores_codex":[0.9989733,0.000266665,0.00005836162,0.0004025013,0.0002058073,0.00009342995],"domain_scores_gemma":[0.9981529,0.000791392,0.00005578103,0.0006921764,0.000224137,0.00008357314],"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":[0.0004405794,0.0003792073,0.0007996005,0.0001182588,0.0002012176,0.0001792709,0.0001743733,0.2747128,0.007763143,0.007838055,0.01108555,0.696308],"study_design_scores_gemma":[0.00001152661,0.00003625706,0.00006750823,0.000007081562,0.00001404784,0.00003358322,0.00001200654,0.9898146,0.002203222,0.007063847,0.0007279044,0.000008397942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01288542,0.0005251577,0.9803969,0.0001081359,0.00008601571,0.00004551439,0.0001536961,0.004950613,0.0008485662],"genre_scores_gemma":[0.2917403,0.0005071217,0.6934192,0.000465851,0.00014093,0.0001814291,0.001866971,0.001042628,0.01063564],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007695785,"threshold_uncertainty_score":0.015302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01808857285752606,"score_gpt":0.2413275181657469,"score_spread":0.2232389453082208,"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."}}