Skip to yearly menu bar Skip to main content

Workshop: Synthetic Data Generation with Generative AI

AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing

Namjoon Suh · Xiaofeng Lin · Din-Yin Hsieh · Mehrdad Honarkhah · Guang Cheng

Keywords: [ Tabular data generation ] [ Auto-encoder ] [ Diffusion model ]

Abstract: 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 upon request and will be publicly released if paper is accepted.

Chat is not available.