Exponential Family Variational Flow Matching for Tabular Data Generation

Andrés Guzmán-Cordero, Floor Eijkelboom, Jan-Willem Van De Meent
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21516-21529, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-guzman-cordero25a, title = {Exponential Family Variational Flow Matching for Tabular Data Generation}, author = {Guzm\'{a}n-Cordero, Andr\'{e}s and Eijkelboom, Floor and Van De Meent, Jan-Willem}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {21516--21529}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/guzman-cordero25a/guzman-cordero25a.pdf}, url = {https://proceedings.mlr.press/v267/guzman-cordero25a.html}, 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.} }
Endnote
%0 Conference Paper %T Exponential Family Variational Flow Matching for Tabular Data Generation %A Andrés Guzmán-Cordero %A Floor Eijkelboom %A Jan-Willem Van De Meent %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-guzman-cordero25a %I PMLR %P 21516--21529 %U https://proceedings.mlr.press/v267/guzman-cordero25a.html %V 267 %X 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.
APA
Guzmán-Cordero, A., Eijkelboom, F. & Van De Meent, J.. (2025). Exponential Family Variational Flow Matching for Tabular Data Generation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:21516-21529 Available from https://proceedings.mlr.press/v267/guzman-cordero25a.html.

Related Material