{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008159376,0.0002969021,0.0002619615,0.0005087435,0.0006597713,0.0002642402,0.002396928,0.0001776647,0.00005245198],"category_scores_gemma":[0.00006670094,0.0003173386,0.000118133,0.00182532,0.0001615344,0.0009911814,0.00002024601,0.0004446219,0.0006661916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001450707,"about_ca_system_score_gemma":0.0001429599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001985199,"about_ca_topic_score_gemma":0.00006056891,"domain_scores_codex":[0.9969789,0.0001665402,0.0006385333,0.001188885,0.0004747628,0.0005523719],"domain_scores_gemma":[0.9965624,0.0007048288,0.0002354961,0.002041404,0.000313677,0.0001421992],"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":[0.0001516654,0.0003089889,0.000009445979,0.00004042007,0.00003594694,0.000008306361,0.0002564092,0.02534718,0.008988457,0.02783456,0.0007428716,0.9362758],"study_design_scores_gemma":[0.00005245197,0.0001493234,0.00006707632,0.00003598531,0.00001334269,0.000002231797,0.000143649,0.8275186,0.1637058,0.004902346,0.003110803,0.0002983844],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001905029,0.0000101041,0.9940888,0.001684654,0.000790284,0.0007652748,0.0002495096,0.002123217,0.00009763159],"genre_scores_gemma":[0.9251577,0.00007769412,0.07337638,0.0002079808,0.0000841291,0.0004971808,0.0003141201,0.00004393562,0.000240895],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9359773,"threshold_uncertainty_score":0.9999279,"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."}}