Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features

TL;DR

This paper introduces a cascaded diffusion model for generating realistic mixed-type tabular data, effectively capturing discrete and continuous features with improved fidelity and a novel guided conditional approach.

Contribution

It proposes a new cascaded flow matching approach that enhances generative modeling of mixed-type tabular data, with formal proofs and superior experimental results.

Findings

Generated samples are more realistic and detailed.

Detection score improves by 51.9%.

Model better captures distributional nuances.

Abstract

Advances in generative modeling have recently been adapted to tabular data containing discrete and continuous features. However, generating mixed-type features that combine discrete states with an otherwise continuous distribution in a single feature remains challenging. We advance the state-of-the-art in diffusion models for tabular data with a cascaded approach. We first generate a low-resolution version of a tabular data row, that is, the collection of the purely categorical features and a coarse categorical representation of numerical features. Next, this information is leveraged in the high-resolution flow matching model via a novel guided conditional probability path and data-dependent coupling. The low-resolution representation of numerical features explicitly accounts for discrete outcomes, such as missing or inflated values, and therewith enables a more faithful generation of mixed-type features. We formally prove that this cascade tightens the transport cost bound. The results indicate that our model generates significantly more realistic samples and captures distributional details more accurately, for example, the detection score improves by 51.9\%. Code is available at https://github.com/muellermarkus/tabcascade.