Usefulness of Quantile-Aware Diffusion Modeling for Highly Imbalanced Tabular Data

Abstract

Classification problem in the context of highly imbalanced data is a major challenge in many real-world applications (e.g., FinTech, healthcare, etc.). In these cases, the vast majority of instances belong to a single class and a small fraction represent the minority class (often the most critical class). Recently, diffusion models have emerged as powerful approaches to reduce the degree of ``imbalanced-ness'' in the dataset; they work by generating synthetic data by capturing complex data distributions using iterative transformations. However, standard diffusion models are not inherently suited to highly skewed or heavy-tailed data, due to inbuilt quadratic error loss, which lacks the structural sensitivity to capture rare, extreme values, and minority-class nuances. We propose a novel approach, namely, Quantile-TabDDPM, based on a quantile-regularized denoising objective that combines the standard quadratic error loss with a quantile loss term to explicitly capture rare events while preserving the theoretical grounding of the original denoising objective. We extensively evaluated our approach on a real-world credit card transaction dataset characterized by extreme class imbalance. The results demonstrate that the integration of diffusion-based synthetic data generation with a quantile-regularized denoising objective provides a robust and effective framework for fraud detection in highly imbalanced datasets.

Beyond Distributional Fidelity: Causal-Penalized Diffusion for Synthetic Tabular Data
Lan Tao, Yongxian He, Shirong Xu +2
arXiv8 Oct 2026PreprintCC BY 4.0Full textStatisticsarXiv
Class-Conditioned Diffusion Augmentation and Explainable In-Context Ensemble Learning for Imbalanced Maintenance Action Classification in Aircraft Systems
Begüm Erol
Mathematics4 Nov 2026Peer-reviewedCC BY 4.0General mathematicsCrossref
Measurement-Error-Aware Causal Distributed-Lag Quantile Modeling of Indoor Air Pollution and Short-Term Lung-Function Deterioration
Shayma Alkobaisi, Anas Ali
arXiv12 Sep 2026PreprintCC BY 4.0Full textStatisticsarXiv
Multiscale modeling of moisture diffusion in polymer/clay nanocomposites
Ali Makhloufi, Djelloul Gueribiz, Frédéric Jacquemin +1
Journal of Reinforced Plastics and Composites28 Oct 2026Peer-reviewedCC BY-NC 4.0Full text2 citedMathematical physics General physicsHAL
Spatio-temporal Latent Denoising Diffusion Probabilistic Models for Reduced-order Modeling of Parametrized Dynamical Systems
Michiel Nikken, Nicolò Botteghi, Federico Califano +1
arXiv15 Sep 2026PreprintCC BY 4.0Full textNumerical analysis & scientific computingarXiv

Cite

BibTeX RIS

BibTeX

@misc{talha2026usefulness,
  title = {{Usefulness of Quantile-Aware Diffusion Modeling for Highly Imbalanced Tabular Data}},
  author = {Abu Talha and Peng Liu and Souradyuti Paul},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.05825},
  eprint = {2610.05825},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.05825},
}

RIS

TY  - UNPB
TI  - Usefulness of Quantile-Aware Diffusion Modeling for Highly Imbalanced Tabular Data
AU  - Abu Talha
AU  - Peng Liu
AU  - Souradyuti Paul
PY  - 2026
DA  - 2026/10/05
PB  - arXiv
DO  - 10.48550/arxiv.2610.05825
UR  - https://arxiv.org/abs/2610.05825
AB  - Classification problem in the context of highly imbalanced data is a major challenge in many real-world applications (e.g., FinTech, healthcare, etc.). In these cases, the vast majority of instances belong to a single class and a small fraction represent the minority class (often the most critical class). Recently, diffusion models have emerged as powerful approaches to reduce the degree of ``imbalanced-ness'' in the dataset; they work by generating synthetic data by capturing complex data distributions using iterative transformations. However, standard diffusion models are not inherently suited to highly skewed or heavy-tailed data, due to inbuilt quadratic error loss, which lacks the structural sensitivity to capture rare, extreme values, and minority-class nuances. We propose a novel approach, namely, Quantile-TabDDPM, based on a quantile-regularized denoising objective that combines the standard quadratic error loss with a quantile loss term to explicitly capture rare events while preserving the theoretical grounding of the original denoising objective. We extensively evaluated our approach on a real-world credit card transaction dataset characterized by extreme class imbalance. The results demonstrate that the integration of diffusion-based synthetic data generation with a quantile-regularized denoising objective provides a robust and effective framework for fraud detection in highly imbalanced datasets.
ER  -

Abstract

Related

Cite