{"id":"W4382237530","doi":"10.1609/aaai.v37i7.26004","title":"A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Defense Acquisition Program Administration; Agency for Defense Development","keywords":"Computer science; Smoothing; Artificial intelligence; Overfitting; Regularization (linguistics); Robustness (evolution); Lipschitz continuity; Machine learning; Classifier (UML); Extractor; Pattern recognition (psychology); Computation; Trimming; Artificial neural network; Algorithm; Mathematics; Computer vision; Engineering","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":[0.004546608,0.00161315,0.002097924,0.001235773,0.001007709,0.001788886,0.003009465,0.00330957,0.002135929],"category_scores_gemma":[0.01443987,0.0007447351,0.001526933,0.001339743,0.002325351,0.003656393,0.003446454,0.004922473,0.001734361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001118806,"about_ca_system_score_gemma":0.002417017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003224586,"about_ca_topic_score_gemma":0.00451033,"domain_scores_codex":[0.9975896,0.0007308107,0.0001046844,0.0007205171,0.0006778279,0.0001765377],"domain_scores_gemma":[0.9931648,0.002395069,0.0005149697,0.00255582,0.001042915,0.0003263646],"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":[0.001081206,0.0004019151,0.003969096,0.0002410378,0.000232046,0.0003023944,0.0004773301,0.3159873,0.04699598,0.04763747,0.01811195,0.5645623],"study_design_scores_gemma":[0.00003663874,0.00006482378,0.0002107015,0.0000153911,0.0000201885,0.00005938537,0.00001661122,0.9741269,0.007324518,0.0159407,0.002160464,0.00002362554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007631549,0.0001542354,0.9896282,0.0002790327,0.00005768596,0.00003927248,0.00005256135,0.001665242,0.0004922374],"genre_scores_gemma":[0.2056206,0.0002913303,0.7864321,0.001032232,0.0002584397,0.000253125,0.0007088392,0.0007439347,0.00465934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004546608,"threshold_uncertainty_score":0.02404505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1866296090457464,"score_gpt":0.309557591752239,"score_spread":0.1229279827064927,"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."}}