AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing
This work addresses the problem of tabular data synthesis for machine learning applications, representing an incremental improvement by integrating existing methods to handle feature correlations.
The paper tackles the challenge of generating synthetic tabular data with heterogeneous features by combining an auto-encoder with a diffusion model, resulting in synthetic tables that show high statistical fidelity and perform well in downstream tasks across 15 datasets.
Diffusion model has become a main paradigm for synthetic data generation in many subfields of modern machine learning, including computer vision, language model, or speech synthesis. In this paper, we leverage the power of diffusion model for generating synthetic tabular data. The heterogeneous features in tabular data have been main obstacles in tabular data synthesis, and we tackle this problem by employing the auto-encoder architecture. When compared with the state-of-the-art tabular synthesizers, the resulting synthetic tables from our model show nice statistical fidelities to the real data, and perform well in downstream tasks for machine learning utilities. We conducted the experiments over $15$ publicly available datasets. Notably, our model adeptly captures the correlations among features, which has been a long-standing challenge in tabular data synthesis. Our code is available at https://github.com/UCLA-Trustworthy-AI-Lab/AutoDiffusion.