RecTable: Fast Modeling Tabular Data with Rectified Flow
Masane Fuchi, Tomohiro Takagi
2025-03-27
Summary
This paper is about creating a new, faster way for AI to generate realistic data tables.
What's the problem?
Existing AI methods for generating data tables can take a long time to train.
What's the solution?
The researchers developed a new method called RecTable that uses a simpler architecture and training strategies to generate data tables more quickly.
Why it matters?
This work matters because it can make it easier and faster to create realistic data for various applications, such as simulations and data augmentation.
Abstract
Score-based or diffusion models generate high-quality tabular data, surpassing GAN-based and VAE-based models. However, these methods require substantial training time. In this paper, we introduce RecTable, which uses the rectified flow modeling, applied in such as text-to-image generation and text-to-video generation. RecTable features a simple architecture consisting of a few stacked gated linear unit blocks. Additionally, our training strategies are also simple, incorporating a mixed-type noise distribution and a logit-normal timestep distribution. Our experiments demonstrate that RecTable achieves competitive performance compared to the several state-of-the-art diffusion and score-based models while reducing the required training time. Our code is available at https://github.com/fmp453/rectable.