Geometry-Aware Tabular Diffusion

Researchers introduced Geometry-Aware Tabular Diffusion (GATD), a method that improves tabular data synthesis by feeding pairwise angles and lengths from column value differences into diffusion denoisers as inputs and auxiliary targets. The MLP-based model achieved state-of-the-art performance on ten datasets while using 3.5x fewer parameters on average, winning 8/10 Shape, 7/10 Trend, and 9/10 downstream utility benchmarks. The findings demonstrate that explicit relational supervision serves as a portable inductive bias for tabular diffusion, with default loss weights also improving performance across GNN and Transformer denoisers.

arXiv:2606.02607v1 Announce Type: new Abstract: Tabular synthesis is critical for privacy-preserving sharing and augmentation, yet diffusion models rely on implicit mechanisms to capture inter-column relationships. We introduce Geometry-Aware Tabular Diffusion GATD , which augments tabular diffusion denoisers with pairwise angles and lengths computed from column value differences and used as inputs and auxiliary targets. Our MLP instantiation achieves state-of-the-art benchmark performance while using 3.5x fewer parameters on average up to 25x for classification tasks : on ten datasets, it wins 8/10 Shape, 7/10 Trend, and 9/10 downstream utility F1/RMSE , reducing Shape and Trend error by 27% and 20%. Default loss weights transfer to GNN and Transformer denoisers, improving Shape on 27/30 and Trend on 25/30 architecture-dataset cells. A matched ablation shows supervision not extra inputs or capacity drives the gain. This shows explicit relational supervision is a portable inductive bias for tabular diffusion.