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:2602. 06806v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes.
By Silpa Vadakkeeveetil Sreelatha, Dan Wang, Serge Belongie, Muhammad Awais, Anjan Dutta
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
The paper proposes a fairness-aware Mixture-of-Experts (MoE) framework that tackles routing-induced bias by applying subgroup reweighting to correct data imbalance and gate entropy regularization to prevent the gating network from collapsing onto subgroup attributes. This end-to-end approach keeps expert utilization balanced and interpretable, offering a clear view of how subgroups are allocated across experts. Experiments show that the method improves fairness while maintaining competitive predictive performance.
By Sunhee Hwang
The paper introduces a control‑variable framework for deep neural networks to mitigate omitted variable bias, particularly shortcut learning where covariates like demographics influence predictions. It refits the final layer of a pre‑trained network using cross‑fitting with ridge penalisation, orthogonalises covariate effects, and marginalises predictions over covariate distributions to achieve unbiased, interpretable results. Experiments on simulated images and neuroimaging data show consistent estimation of true effects and performance close to models trained on unconfounded data.
By Manuel Pfeuffer, Roshan Prakash Rane, Kerstin Ritter, Sonja Greven
arXiv:2608.30699v1 Announce Type: cross
Abstract: Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to...
By Yue Cheng, Jiajun Zhang, Xiaohui Gao, Weiwei Xing, Zhanxing Zhu
arXiv:2607. 14984v1 Announce Type: new Abstract: Per-subgroup fairness audits of medical image classifiers face a sample-size problem: minority subgroups in held-out test sets have so few samples that the resulting confidence intervals on per-subgroup performance are wider than the bias the audit is meant to detect.
By Mahmoud Ibrahim, Bart Elen, Chang Sun, Gokhan Ertaylan, Michel Dumontier
arXiv:2606. 20461v1 Announce Type: new Abstract: Machine learning models have been shown to exhibit discriminatory outcomes or degraded performance for individuals at the intersection of multiple sensitive attributes, such as race and gender.
By Bruno Scarone, Alfredo Viola, Ren\'ee J. Miller
arXiv:2607. 13631v1 Announce Type: new Abstract: The Hessian matrix is an important quantity of interest when it comes to studying the loss landscape and optimization dynamics in deep learning, as well as designing measures of generalization, second-order learning algorithms, etc.
By Jasraj Singh, Enea Monzio Compagnoni, Antonio Orvieto
arXiv:2607. 03770v1 Announce Type: cross Abstract: Prior studies have demonstrated that diffusion classifiers achieve robust zero-shot classification performance.
By Hyunsoo Kim, Jungmyung Wi, Soobin Um, Donghyun Kim, Suhyun Kim
arXiv:2604. 11704v2 Announce Type: replace-cross Abstract: Deep Neural Networks are highly susceptible to shortcut learning, frequently memorizing low-dimensional spurious correlations instead of underlying causal mechanisms.
By Nicolas Rodriguez-Alvarez (Instituto de Educacion Secundaria Parquesol, Valladolid, Spain)
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