Exponential Family Variational Flow Matching for Tabular Data Generation

TL;DR

This paper introduces TabbyFlow, a novel variational flow matching method tailored for generating tabular data with mixed data types, achieving state-of-the-art results.

Contribution

It develops EF-VFM, a new approach that models heterogeneous data using exponential family distributions and learns probability paths efficiently.

Findings

Achieves state-of-the-art performance on tabular data benchmarks.

Effectively models mixed continuous and discrete features.

Provides a principled, data-driven learning framework.

Abstract

While denoising diffusion and flow matching have driven major advances in generative modeling, their application to tabular data remains limited, despite its ubiquity in real-world applications. To this end, we develop TabbyFlow, a variational Flow Matching (VFM) method for tabular data generation. To apply VFM to data with mixed continuous and discrete features, we introduce Exponential Family Variational Flow Matching (EF-VFM), which represents heterogeneous data types using a general exponential family distribution. We hereby obtain an efficient, data-driven objective based on moment matching, enabling principled learning of probability paths over mixed continuous and discrete variables. We also establish a connection between variational flow matching and generalized flow matching objectives based on Bregman divergences. Evaluation on tabular data benchmarks demonstrates state-of-the-art performance compared to baselines.