Local data augmentation for imbalanced binary classification
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.
Related
- Class-Conditioned Diffusion Augmentation and Explainable In-Context Ensemble Learning for Imbalanced Maintenance Action Classification in Aircraft Systems
- Hierarchical Majority Decomposition for Imbalanced Classification: A Recursive Binary Majority-Class Tree with Persistent Minority Comparison
- IFC-HFlowVAE: A self-enhancing generative framework with structural anchoring for imbalanced clinical data augmentation
- Density-Ratio Rescoring for Imbalanced Classification Using Raking Duals and Classifier Scores
- Zero-Complement Extrapolation: Parameter Recovery and Classification in Severely Imbalanced Logistic Regression under Rank-Deficient Regimes
BibTeX
@misc{gueneau2026local,
title = {{Local data augmentation for imbalanced binary classification}},
author = {Harold Guéneau and Alain Celisse and Pascal Delange},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.26418},
eprint = {2610.26418},
archivePrefix = {arXiv},
url = {https://hal.science/hal-05804118v1},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Local data augmentation for imbalanced binary classification
AU - Harold Guéneau
AU - Alain Celisse
AU - Pascal Delange
PY - 2026
DA - 2026/10/19
PB - HAL
DO - 10.48550/arxiv.2610.26418
UR - https://hal.science/hal-05804118v1
AB - 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.
ER -