{"id":"W3169315049","doi":"10.1007/s10994-021-06080-w","title":"On the benefits of representation regularization in invariance based domain generalization","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Mila - Quebec Artificial Intelligence Institute; Vector Institute; Western University; Université Laval","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institute for Advanced Research","keywords":"Regularization (linguistics); Invariant (physics); Computer science; Generalization error; Artificial intelligence; Representation (politics); Generalization; Machine learning; Feature learning; Robustness (evolution); Algorithm; Mathematics; Unsupervised 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002685024,0.0009090131,0.001179971,0.0007831973,0.0007548933,0.0009370748,0.001732043,0.001495657,0.001390861],"category_scores_gemma":[0.009696527,0.0003958813,0.001065241,0.0008264438,0.002041762,0.003006952,0.003071974,0.002901051,0.000632932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007356812,"about_ca_system_score_gemma":0.001051117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002399437,"about_ca_topic_score_gemma":0.001908913,"domain_scores_codex":[0.9987817,0.000448842,0.00004993724,0.0003713851,0.0002458372,0.0001023404],"domain_scores_gemma":[0.9966157,0.001614,0.0002614338,0.001038745,0.0003139738,0.0001560354],"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":[0.0002218724,0.000241731,0.002548186,0.0001170115,0.0001166323,0.0002036152,0.0003332594,0.6598622,0.01930919,0.07636348,0.004527115,0.2361557],"study_design_scores_gemma":[0.000008071393,0.0000512586,0.0002277162,0.000006905382,0.000008782202,0.00004953549,0.00001641605,0.9761308,0.001654292,0.02126587,0.0005687036,0.00001159625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02001654,0.0002470842,0.9778994,0.0003090921,0.00002684255,0.00003697558,0.00002768625,0.0004817949,0.0009545778],"genre_scores_gemma":[0.6657709,0.0004978724,0.3292849,0.0006429783,0.0001562174,0.0001665221,0.0003541668,0.0003305034,0.00279601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002685024,"threshold_uncertainty_score":0.01419991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02131954762480759,"score_gpt":0.2423029124869489,"score_spread":0.2209833648621413,"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."}}