{"id":"W4385213925","doi":"10.1109/tai.2023.3298297","title":"Contrastive-Enhanced Domain Generalization With Federated Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Normalization (sociology); Classifier (UML); Artificial intelligence; Generalization; Embedding; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003424323,0.0002018118,0.0001732098,0.0003140734,0.0007738387,0.0003584122,0.0003006489,0.00008018629,0.0001211881],"category_scores_gemma":[0.00002058585,0.0001904251,0.00006591214,0.001904524,0.0000930886,0.0004335508,0.000002841279,0.0003610793,0.001056387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006227203,"about_ca_system_score_gemma":0.00008235834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002600763,"about_ca_topic_score_gemma":0.0001025106,"domain_scores_codex":[0.9981852,0.0001912784,0.0003434269,0.0004999875,0.000389361,0.0003908085],"domain_scores_gemma":[0.9991657,0.0001981952,0.0001095404,0.0002177275,0.0001814063,0.0001275021],"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":[0.00007633996,0.00007442582,0.000002710816,0.00000509712,0.00002580026,0.00001834425,0.001948758,0.7079611,0.02553602,0.01296584,0.00002086257,0.2513646],"study_design_scores_gemma":[0.00009714971,0.0002932514,0.00005026624,0.00004183914,0.000007567332,0.000007413963,0.001087643,0.7352392,0.2595172,0.00270898,0.0006365809,0.0003128793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01985892,0.000005353937,0.976833,0.0005270672,0.000511373,0.0002270327,0.000001985752,0.000963914,0.001071401],"genre_scores_gemma":[0.989305,0.00003084931,0.009310862,0.0002168682,0.0000403269,0.00005711786,0.000005676255,0.00002389588,0.001009461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.969446,"threshold_uncertainty_score":0.9997214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04008017325056603,"score_gpt":0.28246220511734,"score_spread":0.242382031866774,"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."}}