Abstract
The generation of synthetic tabular data plays a critical role in applications such as data enhancement, privacy preservation, and model validation. However, the heterogeneity of tabular data—comprising both continuous and categorical features with intricate interdependencies—presents significant challenges in generating high-quality data. This study presents the Dual-Scale Diffusion Probabilistic Method (DSDDPM), a novel framework developed to improve the performance of the Denoising Diffusion Probabilistic Model (DDPM) for tabular data generation. DSDDPM tackles the challenge of capturing both global dependencies and local details through the use of a dual-scale noise-handling mechanism. It models the global structure at the coarse scale and the regional patterns at the fine scale throughout the forward and backward diffusion processes. Experimental evaluations on several benchmark tabular datasets show that DSDDPM outperforms existing state-of-the-art methods. Specifically, compared to other methods, DSDDPM improves machine learning efficiency by an average of 5-7%. In terms of global dependency modeling, DSDDPM exhibits the lowest correlation deviation across all datasets. Moreover, in detail consistency, DSDDPM shows the highest alignment of feature distributions between the generated data and real data, significantly outperforming other methods. These results position DSDDPM as a robust and scalable solution for generating high-quality synthetic tabular data, enhancing fidelity and versatility across various applications.
Funding Information
  • Anhui Provincial Key Natural Science Foundation Project: Research on Pavement Defect Detection Method Based on Deep Learning (2023AH052699)
  • Anhui Provincial Key Natural Science Foundation Project: High-Frequency Modeling and Application Research of Multiphase Peak Current Mode Buck Power Converter in Industrial Internet (2022AH052364)