SAGE (Subpopulation-Aware Generative Enhancement) is a two-stage generative augmentation framework designed to mitigate spurious correlations in machine learning when group labels are unavailable. It uses cluster-derived sub-labels and class labels to fine‑tune a conditional generative model and text encoder, producing synthetic data that fills underrepresented regions and creates a balanced validation set for last‑layer reweighting. Experiments show SAGE improves worst‑group accuracy to 89.5%, 85.7%, and 79.1% on Waterbirds, CelebA, and MetaShift, outperforming existing group‑label‑free baselines by up to 7.7 percentage points.
By Yiming Luo, Rongqiang Zhao, Jie Liu
arXiv:2505. 13518v3 Announce Type: replace-cross Abstract: Imbalanced datasets, where one class significantly outnumbers others, remain a persistent challenge in machine learning, often biasing predictions toward the majority class and degrading classifier performance.
By Behnam Yousefimehr, Mehdi Ghatee, Javad Fazli, Shervin Ghaffari, Zahra Rafei, Mohammad Amin Seifi, Sajed Tavakoli, Abolfazl Nikahd, Mahdi Razi Gandomani, Alireza Orouji, Ramtin Mahmoudi Kashani, Sarina Heshmati, Negin Sadat Mousavi
arXiv:2606. 01221v1 Announce Type: cross Abstract: Imbalanced learning is a critical challenge in machine learning, where underrepresented target values can bias models and degrade prediction performance on rare but important cases.
By Shermin Shahbazi, Hossein Mohammadi, Mohsen Afsharchi
The paper introduces a bias‑correction method for synthetic oversampling in imbalanced learning. It estimates the loss discrepancy caused by the data generator using a held‑out majority subset and transfers this correction to the minority class under a uniform bias‑transfer assumption. The authors provide finite‑sample bounds for bias transfer and excess balanced risk, identify when SMOTE introduces significant bias, and demonstrate the method’s applicability to multi‑task learning and propensity‑score estimation, with empirical results showing greatest benefit when synthetic distortion is large.
By Pengfei Lyu, Zhengchi Ma, Linjun Zhang, Anru R. Zhang
arXiv:2610.27728v1 Announce Type: new
Abstract: Real-world datasets are inherently class-imbalanced, leading models to favor majority classes and struggle with minority ones. Existing logit adjustmen...
By Jiyoung Lim, Jee-Hyong Lee
arXiv:2607. 17178v1 Announce Type: cross Abstract: Imbalanced learning addresses predictive modeling problems with underrepresented regions of the data distribution.
By Shermin Shahbazi, Hossein Mohammadi, Mohsen Afsharchi
The paper surveys tabular imbalanced learning and introduces TILBench, a benchmark evaluating over 40 methods on 57 datasets. It presents a unified taxonomy of approaches and shows that no single method dominates across all settings, with performance depending on dataset regimes and computational constraints. Practical recommendations for method selection and future research directions are provided.
By Ruizhe Liu, Jiaqi Luo
arXiv:2501. 15790v2 Announce Type: replace Abstract: Synthetic minority oversampling is typically designed and evaluated against a predictive objective, generating samples that improve downstream classification.
By Pankaj Yadav, Vivek Vijay
arXiv:2606. 10250v1 Announce Type: cross Abstract: Class imbalance is a common problem in deep learning that severely degrades performance.
By Haengbok Chung, Jae Sung Lee
Real-world datasets are inherently class-imbalanced, leading models to favor majority classes and struggle with minority ones. Existing logit adjustment methods address this by modifying logits based...
arXiv:2506. 01486v2 Announce Type: replace Abstract: Data imbalance persists as a pervasive challenge in regression tasks, introducing bias in model performance and undermining predictive reliability.
By Jelke Wibbeke, Sebastian Rohjans, Andreas Rauh
arXiv:2608. 09221v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training across distributed client devices while preserving data privacy.
By Radwan Selo, Majid Kundroo, Taehong Kim