RecTable: Fast Modeling Tabular Data with Rectified Flow
This work addresses the training efficiency bottleneck for researchers and practitioners using generative models on tabular data, though it is incremental as it builds on existing rectified flow methods.
The paper tackles the problem of slow training in score-based or diffusion models for tabular data generation by introducing RecTable, which uses rectified flow modeling and achieves competitive performance while reducing training time.
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.