Understanding Latent Flow Models for Tabular Data Synthesis: Targets, Paths, and Sampling
For practitioners generating synthetic tabular data in regulated domains, this study offers empirical defaults to navigate the trade-offs between analytical utility, disclosure risk, and computational budget.
The paper empirically evaluates latent flow models for tabular data synthesis across seven datasets, finding that learning targets (velocity/posterior matching) yield higher utility while score/noise matching reduce disclosure risk, and that optimal transport paths enable compute savings. It provides actionable configuration guidance for balancing utility, risk, and cost.
Synthetic tabular data enables microdata sharing in regulated domains, yet deploying continuous-time generative models requires balancing analytical utility, disclosure risk, and computational cost. Latent-space flow models are flexible, but theoretical equivalences across learning targets, probability paths, and sampling dynamics can translate into different behaviour under finite-step integration and explicit compute budgets. We present an empirical study of tabular latent flow models across seven datasets, evaluating velocity, score, noise, and posterior matching objectives under optimal transport (OT) and variance-preserving (VP) paths, ODE and SDE sampling, and varying integration budgets. Our contributions are threefold: (1) we show that the learning target largely determines the utility-risk operating regime, with velocity and posterior matching tending to yield higher utility, while score and noise matching tend to achieve lower disclosure risk; (2) we demonstrate that configuration and sampling choices shift performance, with midpoint often improving distributional fidelity and OT paths often tolerating earlier stopping than VP, enabling compute savings under fixed budgets or risk thresholds; and (3) we distil these findings into actionable defaults and practical configuration guidance to support pre-release model selection under disclosure risk and resource constraints. The code implementation and supplementary materials can be accessed in https://github.com/rulnasution/tabular-latent-flow/.