{"id":"W4415254920","doi":"10.1016/j.ins.2025.122804","title":"Federated domain generalization with source knowledge preservation via discriminative ensembles","year":2025,"lang":"en","type":"article","venue":"Information Sciences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Information Technology Research Centre; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; Ministry of Education, Ethiopia","keywords":"Discriminative model; Generalization; Regularization (linguistics); Benchmark (surveying); Ensemble learning; Feature (linguistics); Domain (mathematical analysis); Adversarial system; Labeled data","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006747075,0.00009923685,0.00008285833,0.000323659,0.0006850613,0.0008713767,0.0004880253,0.00003855743,0.000006001838],"category_scores_gemma":[0.0001129409,0.00007238582,0.0000152886,0.001560756,0.0001154813,0.006166439,0.0001088446,0.0000699244,0.000045575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000551564,"about_ca_system_score_gemma":0.0002539275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001173403,"about_ca_topic_score_gemma":0.00007162479,"domain_scores_codex":[0.9989786,0.0001150085,0.000267442,0.0001894241,0.0002955573,0.0001539761],"domain_scores_gemma":[0.9992341,0.00008733361,0.0001928405,0.0001789907,0.0002737212,0.00003295998],"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":[0.00001918241,0.00006329128,0.005918646,0.00006979848,0.00001644739,2.014073e-7,0.01430586,0.00958563,0.0007999333,0.4788866,0.002739548,0.4875949],"study_design_scores_gemma":[0.0002813835,0.00007590343,0.01672819,0.00004368308,0.000003816694,0.000003019854,0.0006557194,0.926523,0.001332504,0.00428701,0.04991779,0.0001479455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01259124,0.00002579687,0.9493304,0.002678917,0.0001191951,0.0001619566,0.000001381521,0.0001791184,0.03491198],"genre_scores_gemma":[0.9756052,0.000005672651,0.02295929,0.0005103714,0.00001594119,0.00003358278,0.00007405388,0.000001773403,0.000794149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9630139,"threshold_uncertainty_score":0.8402705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01684071150768637,"score_gpt":0.2873510741744416,"score_spread":0.2705103626667553,"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."}}