{"id":"W4376464555","doi":"10.1109/tai.2023.3275133","title":"Margin-Aware Adaptive-Weighted-Loss for Deep Learning Based Imbalanced Data Classification","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Overfitting; Computer science; Softmax function; Margin (machine learning); Artificial intelligence; Machine learning; Discriminative model; MNIST database; Leverage (statistics); Robustness (evolution); Class (philosophy); Pattern recognition (psychology); Deep learning; Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004863163,0.001588286,0.001475904,0.001055938,0.0005802643,0.001078177,0.00289088,0.001580987,0.001709342],"category_scores_gemma":[0.007446568,0.0004463658,0.0006878033,0.001142705,0.001372214,0.002905739,0.002808549,0.003022531,0.0008139919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001575973,"about_ca_system_score_gemma":0.001336831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001292787,"about_ca_topic_score_gemma":0.001496051,"domain_scores_codex":[0.9982336,0.0005389939,0.0001227565,0.0003551138,0.0005436436,0.0002058978],"domain_scores_gemma":[0.9977251,0.00090213,0.000287218,0.0004814784,0.0004654608,0.0001387078],"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":[0.0007610339,0.000546905,0.004021171,0.0002170541,0.0001511544,0.0001402017,0.0002142269,0.4585989,0.008886822,0.01859397,0.01244457,0.495424],"study_design_scores_gemma":[0.00001592201,0.0000745479,0.0003009881,0.00001598794,0.000009383368,0.00002623532,0.00001328062,0.98246,0.002416005,0.01390287,0.0007560857,0.000008770568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0272381,0.0006926465,0.9687153,0.0004540263,0.0000953742,0.0000938798,0.000174503,0.001503143,0.001033154],"genre_scores_gemma":[0.7455297,0.0005196207,0.2465026,0.0007249002,0.0002182129,0.0005208603,0.001159786,0.000358151,0.004466193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004863163,"threshold_uncertainty_score":0.02571917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1405798030758225,"score_gpt":0.344833698031445,"score_spread":0.2042538949556226,"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."}}