aiqbench analysis
This research introduces ctdGAN, a conditional Generative Adversarial Network designed specifically to address class imbalance in tabular datasets by leveraging probabilistic sampling of latent subspaces. By partitioning input space and penalizing cluster/class mis-predictions, the model generates high-fidelity synthetic data that better preserves the original distribution's structure compared to standard GAN approaches. The study demonstrates improved classification accuracy across 14 imbalanced datasets, offering a practical solution for enhancing machine learning performance in relational database environments.
A Conditional GAN for Tabular Data Generation with Probabilistic Sampling of Latent Subspaces
arXiv:2508.00472v3 Announce Type: replace Abstract: The tabular form constitutes the standard way of representing data in relational database systems and spreadsheets. But, similarly to other forms, tabular data suffers from class imbalance, a problem that causes serious performance degradation in a wide variety of machine learning tasks. One of the most effective solutions dictates the usage of Generative Adversarial Networks (GANs) in order to synthesize artificial data instances for the under-represented classes. Despite their good performance, most of the proposed GAN models do not take into account the vector subspaces of the input samples in the real data space, leading to data generation in arbitrary locations. In addition, the class labels are handled in the same manner as the other categorical variables, so conditional sampling by class is rendered less effective. To overcome these problems, this study presents ctdGAN, a conditional GAN for alleviating class imbalance in tabular datasets. Initially, ctdGAN executes a space partitioning step to assign cluster labels to the input samples. Subsequently, it utilizes these labels to synthesize samples via a novel probabilistic sampling strategy and a new loss function that penalizes both cluster and class mis-predictions. In this way, ctdGAN generates samples in subspaces that resemble those of the original data distribution. We also introduce several other improvements, including a simple, yet effective cluster-wise scaling technique that captures multiple feature modes without affecting data dimensionality. The evaluation of ctdGAN with 14 imbalanced datasets demonstrated its strong ability in generating high fidelity samples and improving classification accuracy.
Abstract:The tabular form constitutes the standard way of representing data in relational database systems and spreadsheets. But, similarly to other forms, tabular data suffers from class imbalance, a problem that causes serious performance degradation in a wide variety of machine learning tasks. One of the most effective solutions dictates the usage of Generative Adversarial Networks (GANs) in order to synthesize artificial data instances for the under-represented classes. Despite their good performance, most of the proposed GAN models do not take into account the vector subspaces of the input samples in the real data space, leading to data generation in arbitrary locations. In addition, the class labels are handled in the same manner as the other categorical variables, so conditional sampling by class is rendered less effective. To overcome these problems, this study presents ctdGAN, a conditional GAN for alleviating class imbalance in tabular datasets. Initially, ctdGAN executes a space partitioning step to assign cluster labels to the input samples. Subsequently, it utilizes these labels to synthesize samples via a novel probabilistic sampling strategy and a new loss function that penalizes both cluster and class mis-predictions. In this way, ctdGAN generates samples in subspaces that resemble those of the original data distribution. We also introduce several other improvements, including a simple, yet effective cluster-wise scaling technique that captures multiple feature modes without affecting data dimensionality. The evaluation of ctdGAN with 14 imbalanced datasets demonstrated its strong ability in generating high fidelity samples and improving classification accuracy.
Machine Learning (cs.LG)
arXiv:2508.00472 [cs.LG]
(or arXiv:2508.00472v3 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2508.00472 Focus to learn more arXiv-issued DOI via DataCite
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 · 337 words
Related coverage
TabGift: A Context-Efficient Foundation Model for Tabular Data Generation
arXiv · Oct 15, 2026
BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generation
arXiv · Jun 9, 2026
Efficient Flow Matching using Latent Variables
arXiv · Jun 16, 2026
SimCast-S2S: An Efficient Generative Model for Subseasonal Precipitation Forecasting via Transfer Learning from Climate Simulations
arXiv · Aug 28, 2026