{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009173052,0.0003633295,0.000326845,0.001204103,0.0004002623,0.0007893211,0.0005611565,0.0002699941,0.000004315572],"category_scores_gemma":[0.0001993823,0.0003898328,0.00004771562,0.001079214,0.0001730048,0.0009372759,0.0004763062,0.000764946,0.00001148047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003403967,"about_ca_system_score_gemma":0.0003140426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006509188,"about_ca_topic_score_gemma":0.0002834326,"domain_scores_codex":[0.9972334,0.00008631485,0.0004610312,0.00118027,0.0006036984,0.0004352816],"domain_scores_gemma":[0.9988445,0.0002281536,0.0003192408,0.0002473604,0.0002620569,0.00009865821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006955149,0.000008229676,0.000333399,0.00003321412,0.000004982266,0.00001213818,0.004085459,0.7133743,0.001472212,0.007904419,0.000002071525,0.2727626],"study_design_scores_gemma":[0.0002656659,0.00007315908,0.0003320615,0.0001903273,0.000003632406,0.00001510394,0.000001961094,0.9714724,0.0001396385,0.02709509,0.00001999541,0.0003909693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003653987,0.00009731598,0.9975611,0.0001985883,0.0003845627,0.0003136181,7.463069e-7,0.0002550347,0.0008236448],"genre_scores_gemma":[0.8143361,0.00005181085,0.1838402,0.0005718706,0.0001372931,0.00001373703,0.00003438204,0.00005973538,0.0009549545],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8139706,"threshold_uncertainty_score":0.9998553,"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."}}