aiqbench analysis
This research addresses the challenge of imbalanced binary classification by demonstrating that local data augmentation significantly outperforms simple rebalancing or standard methods like SMOTE. The study specifically highlights the efficacy of combining anchor point subsampling near the decision boundary with Gaussian or diffusion-based kernels to improve recall while controlling false detections.
Local data augmentation for imbalanced binary classification
arXiv:2610.26418v1 Announce Type: cross Abstract: Facing imbalanced binary classification, we aim at maximizing the recall while limiting the proportion of false detections in the minority class. For doing that, the present work studies the effect of several rebalancing strategies, from the uniform subsampling of the observations from the minority class, to a more involved local data augmentation scheme. To be more specific, we establish that only rebalancing class proportions cannot modify the classification performance, whereas local data augmentation is proved to have an impact on the final results. The local augmentation scheme is introduced by means of a two-step procedure. The first step randomly subsamples anchor points among the training observations. These anchor points are used in the second step, for drawing new augmentation data following an ''augmentation kernel'' to be specified. This enables us to decouple the impact of the anchor points subsampling from the one of drawing augmentation data accounting (or not) for the local geometry of the support. The experiments on synthetic data illustrate the practical performance of several strategies for subsampling anchor points combined with either a Gaussian or a diffusion-based augmentation kernel. Compared to SMOTE-like data augmentation procedures, a better performance is achieved when subsampling in the close neighborhood to the classification boundary combined with a Gaussian augmentation kernel. Furthermore in specific settings where the geometric structure of the support matters, the experimental results show that using a diffusion-based augmentation kernel outperforms the Gaussian one.
Abstract:Facing imbalanced binary classification, we aim at maximizing the recall while limiting the proportion of false detections in the minority class. For doing that, the present work studies the effect of several rebalancing strategies, from the uniform subsampling of the observations from the minority class, to a more involved local data augmentation scheme. To be more specific, we establish that only rebalancing class proportions cannot modify the classification performance, whereas local data augmentation is proved to have an impact on the final results. The local augmentation scheme is introduced by means of a two-step procedure. The first step randomly subsamples anchor points among the training observations. These anchor points are used in the second step, for drawing new augmentation data following an ''augmentation kernel'' to be specified. This enables us to decouple the impact of the anchor points subsampling from the one of drawing augmentation data accounting (or not) for the local geometry of the support. The experiments on synthetic data illustrate the practical performance of several strategies for subsampling anchor points combined with either a Gaussian or a diffusion-based augmentation kernel. Compared to SMOTE-like data augmentation procedures, a better performance is achieved when subsampling in the close neighborhood to the classification boundary combined with a Gaussian augmentation kernel. Furthermore in specific settings where the geometric structure of the support matters, the experimental results show that using a diffusion-based augmentation kernel outperforms the Gaussian one.
Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Statistics Theory (math.ST); Machine Learning (stat.ML)
arXiv:2610.26418 [cs.AI]
(or arXiv:2610.26418v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.26418 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 338 words
Related coverage
On the Reliability of Generative Augmentation: A Wasserstein-Based Theoretical and Empirical Study
arXiv · Sep 2, 2026
ANN Search: Recall What Matters
arXiv · Jun 5, 2026
Structural Preservation Governs Data Augmentation in Deep Learning-Based Laser Speckle Material Classification
arXiv · Jul 28, 2026
Enhancing Sentiment Classification on Small Datasets through Data Augmentation and Transfer Learning
arXiv · Nov 2, 2026