{"ID":2839333,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17629","arxiv_id":"2511.17629","title":"Boundary-Aware Adversarial Filtering for Reliable Diagnosis under Extreme Class Imbalance","abstract":"We study classification under extreme class imbalance where recall and calibration are both critical, for example in medical diagnosis scenarios. We propose AF-SMOTE, a mathematically motivated augmentation framework that first synthesizes minority points and then filters them by an adversarial discriminator and a boundary utility model. We prove that, under mild assumptions on the decision boundary smoothness and class-conditional densities, our filtering step monotonically improves a surrogate of F_beta (for beta \u003e= 1) while not inflating Brier score. On MIMIC-IV proxy label prediction and canonical fraud detection benchmarks, AF-SMOTE attains higher recall and average precision than strong oversampling baselines (SMOTE, ADASYN, Borderline-SMOTE, SVM-SMOTE), and yields the best calibration. We further validate these gains across multiple additional datasets beyond MIMIC-IV. Our successful application of AF-SMOTE to a healthcare dataset using a proxy label demonstrates in a disease-agnostic way its practical value in clinical situations, where missing true positive cases in rare diseases can have severe consequences.","short_abstract":"We study classification under extreme class imbalance where recall and calibration are both critical, for example in medical diagnosis scenarios. We propose AF-SMOTE, a mathematically motivated augmentation framework that first synthesizes minority points and then filters them by an adversarial discriminator and a boun...","url_abs":"https://arxiv.org/abs/2511.17629","url_pdf":"https://arxiv.org/pdf/2511.17629v2","authors":"[\"Yanxuan Yu\",\"Michael S. Hughes\",\"Julien Lee\",\"Jiacheng Zhou\",\"Andrew F. Laine\"]","published":"2025-11-19T02:15:58Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}