EUVIMEDEUVIMED entdecken
Crossref

TabGeoFlow: A Geometric Flow Matching Model for Tabular Data Synthesis

Jong In Choi

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (25) · 20562-20569

DOI: 10.1609/aaai.v40i25.39192 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jong In Choi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tabular data synthesis is a key technique for protecting data privacy and addressing class imbalance, yet existing generative models struggle to capture the complex intrinsic structure of the data. To overcome this limitation, we propose TabGeoFlow, a novel geometric flow matching model for tabular data synthesis. The core innovation of TabGeoFlow is the injection of an explicit geometric inductive bias into the conditional flow matching framework. We decompose the learned vector field into local tangent and normal components of the data manifold. By dynamically suppressing the predicted normal component via a controlling loss function, we constrain the generative path to follow the data's intrinsic structure. Implemented with a shared backbone for parameter efficiency, TabGeoFlow achieves competitive or better fidelity and utility, while exhibiting near random black box MIA accuracy and DCR ≈ 50%, suggesting reduced memorization without sacrificing quality.

Zitieren

APA

Choi, J. I. (2026). TabGeoFlow: A Geometric Flow Matching Model for Tabular Data Synthesis. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 20562-20569. https://doi.org/10.1609/aaai.v40i25.39192

Vancouver

Choi JI. TabGeoFlow: A Geometric Flow Matching Model for Tabular Data Synthesis. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(25):20562-20569. doi:10.1609/aaai.v40i25.39192

BibTeX
@article{Choi2026,
  author = {Choi, Jong In},
  title = {TabGeoFlow: A Geometric Flow Matching Model for Tabular Data Synthesis},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {25},
  pages = {20562--20569},
  doi = {10.1609/aaai.v40i25.39192}
}
Kostenlos starten →