Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features
This work addresses a specific problem in generative modeling for heterogeneous tabular data, offering incremental improvements over existing methods.
The paper tackled the challenge of generating realistic tabular data with mixed-type features (discrete and continuous) by proposing a cascaded flow matching approach, resulting in a 40% increase in detection score for more accurate sample generation.
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 increases by 40%.