AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

TabGeoFlow: A Geometric Flow Matching Model for Tabular Data Synthesis

Jong In Choi

AAAI 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow matching and flow sampling · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add structural flow regularization (SFR) loss (ablation)TabGeoFlow · AdultTSTR AUC: .898 -> .913Improved
add structural flow regularization (SFR) loss (ablation)TabGeoFlow · DefaultTSTR AUC: .745 -> .761Improved
add SFR loss (ablation)TabGeoFlow · Adult / DefaultDCR % (distance from 50): Adult 51.11 -> 50.37; Default 48.46 -> 50.19Mixed
use dynamic threshold instead of fixed (ablation)TabGeoFlow · AdultTSTR AUC: .903 -> .913Improved
use dynamic threshold instead of fixed (ablation)TabGeoFlow · DefaultTSTR AUC: .760 -> .761No clear effect
vary tangent dimension k (10, 20, 40 vs 30) (ablation)TabGeoFlow · AdultTSTR AUC: .903-.909 vs .913No clear effect
use TabGeoFlow instead of TabDiff for privacytabular synthesizer · DCR average over 7 datasetsDCR %: 52.06 -> 50.45Improved
use TabGeoFlow instead of TabDiff for fidelitytabular synthesizer · Shape error averageshape error rate %: 1.24 -> 1.34No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy