CTTVAE: Latent Space Structuring for Conditional Tabular Data Generation on Imbalanced Datasets

TL;DR

CTTVAE introduces a novel conditional variational autoencoder with class-aware latent structuring and adaptive sampling, significantly improving synthetic data quality for minority classes in imbalanced tabular datasets.

Contribution

It proposes CTTVAE with a triplet margin loss and targeted sampling, enhancing minority class representation without destabilizing training.

Findings

Outperforms existing models on minority class utility across six benchmarks.

Achieves better class representation and downstream task performance.

Maintains competitive data fidelity and privacy considerations.

Abstract

Generating synthetic tabular data under severe class imbalance is essential for domains where rare but high-impact events drive decision-making. However, most generative models either overlook minority groups or fail to produce samples that are useful for downstream learning. We introduce CTTVAE, a Conditional Transformer-based Tabular Variational Autoencoder equipped with two complementary mechanisms: (i) a class-aware triplet margin loss that restructures the latent space for sharper intra-class compactness and inter-class separation, and (ii) a training-by-sampling strategy that adaptively increases exposure to underrepresented groups. Together, these components form CTTVAE+TBS, a framework that consistently yields more representative and utility-aligned samples without destabilizing training. Across six real-world benchmarks, CTTVAE+TBS achieves the strongest downstream utility on minority classes, often surpassing models trained on the original imbalanced data while maintaining competitive fidelity and bridging the gap for privacy for interpolation-based sampling methods and deep generative methods. Ablation studies further confirm that both latent structuring and targeted sampling contribute to these gains. By explicitly prioritizing downstream performance in rare categories, CTTVAE+TBS provides a robust and interpretable solution for conditional tabular data generation, with direct applicability to industries such as healthcare, fraud detection, and predictive maintenance where even small gains in minority cases can be critical.