{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001066561,0.0004455876,0.0004569161,0.0002982828,0.0005573501,0.0005799207,0.002613412,0.0002060077,0.0000452543],"category_scores_gemma":[0.0004963296,0.0003354918,0.0000849524,0.001782856,0.0004048316,0.001039728,0.0006116824,0.0009568632,0.0002566156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009364002,"about_ca_system_score_gemma":0.0002735454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004790499,"about_ca_topic_score_gemma":0.0001269481,"domain_scores_codex":[0.9964621,0.00007505976,0.0007159256,0.001116923,0.0009562342,0.0006737443],"domain_scores_gemma":[0.9973992,0.0004058364,0.0006876499,0.0006619999,0.0006522763,0.0001930705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002520896,0.0002920591,0.0006694124,0.00005139587,0.00009536206,0.00000531658,0.01006688,0.001030744,0.06672517,0.7229439,0.0004456237,0.197422],"study_design_scores_gemma":[0.000197544,0.0003657974,0.001619259,0.0004848416,0.00004418169,0.000006253431,0.003547797,0.8789021,0.02609055,0.08797271,0.0002150373,0.0005538656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3189858,0.00006619797,0.638441,0.02358732,0.001068763,0.001101578,0.00006810632,0.001356344,0.01532487],"genre_scores_gemma":[0.9748106,0.00003256602,0.02368394,0.0005808224,0.0001313835,0.00005881586,0.00001314085,0.00004393395,0.0006448029],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8778714,"threshold_uncertainty_score":0.9999097,"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."}}