Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Class

TL;DR

This paper introduces a novel pre-processing technique that converts binary class labels into ternary labels by adding an overlap class, significantly improving the quality of synthetic data and classifier accuracy in imbalanced tabular datasets.

Contribution

The paper proposes a new method of handling class imbalance by introducing an overlap class, enhancing the performance of deep generative models and classifiers on tabular data.

Findings

Improved quality of synthetic minority class data.

Enhanced classifier accuracy on imbalanced datasets.

Effective across multiple datasets and models.

Abstract

Handling imbalance in class distribution when building a classifier over tabular data has been a problem of long-standing interest. One popular approach is augmenting the training dataset with synthetically generated data. While classical augmentation techniques were limited to linear interpolation of existing minority class examples, recently higher capacity deep generative models are providing greater promise. However, handling of imbalance in class distribution when building a deep generative model is also a challenging problem, that has not been studied as extensively as imbalanced classifier model training. We show that state-of-the-art deep generative models yield significantly lower-quality minority examples than majority examples. %In this paper, we start with the observation that imbalanced data training of generative models trained imbalanced dataset which under-represent the minority class. We propose a novel technique of converting the binary class labels to ternary class labels by introducing a class for the region where minority and majority distributions overlap. We show that just this pre-processing of the training set, significantly improves the quality of data generated spanning several state-of-the-art diffusion and GAN-based models. While training the classifier using synthetic data, we remove the overlap class from the training data and justify the reasons behind the enhanced accuracy. We perform extensive experiments on four real-life datasets, five different classifiers, and five generative models demonstrating that our method enhances not only the synthesizer performance of state-of-the-art models but also the classifier performance.