Synthetic data generation is an important tool for privacy-preserving data sharing. While diffusion models have set recent benchmarks, flow matching (FM) offers a promising alternative. This paper presents different ways to implement flow matching for tabular data synthesis. We provide a comprehensive empirical study that compares flow matching (FM and variational FM) with a state-of-the-art diffusion method (TabDDPM and TabSyn) in tabular data synthesis. We evaluate both the standard Optimal Transport (OT) and the Variance Preserving (VP) probability paths, and also compare deterministic and stochastic samplers -- something possible when learning to generate using \textit{variational} flow matching -- characterising the empirical relationship between data utility and privacy risk. Our key findings reveal that flow matching, particularly TabbyFlow, outperforms diffusion baselines. Flow matching methods also achieves better performance with remarkably low function evaluations ($\leq$ 100 steps), offering a substantial computational advantage. The choice of probability path is also crucial, as using the OT path demonstrates superior performance, while VP has potential for producing synthetic data with lower disclosure risk. Lastly, our results show that making flows stochastic not only preserves marginal distributions but, in some instances, enables the generation of high utility synthetic data with reduced disclosure risk.

翻译：合成数据生成是隐私保护数据共享的重要工具。虽然扩散模型近期确立了基准性能，但流匹配（FM）提供了一种有前景的替代方案。本文提出了实现表格数据合成流匹配的不同方法。我们通过全面的实证研究，在表格数据合成任务中比较了流匹配（FM及变分流匹配）与最先进的扩散方法（TabDDPM和TabSyn）。我们评估了标准最优传输（OT）和方差保持（VP）概率路径，并比较了确定性与随机采样器——这在学习使用\textit{变分}流匹配进行生成时成为可能——从而刻画了数据效用与隐私风险之间的经验关系。我们的核心发现表明，流匹配方法（尤其是TabbyFlow）优于扩散基线。流匹配方法还能以极低的函数评估次数（$\leq$ 100步）实现更优性能，提供了显著的计算优势。概率路径的选择也至关重要：使用OT路径展现出更优越的性能，而VP路径在生成低披露风险的合成数据方面具有潜力。最后，我们的结果表明，使流过程随机化不仅能保持边缘分布，在某些情况下还能生成具有高效用且披露风险降低的合成数据。