用修正流加速表格数据生成，训练时间更短。
RecTable: Fast Modeling Tabular Data with Rectified Flow
- 基于修正流构建简单架构，仅用少量门控线性单元块
- 混合噪声与对数正态时间步分布，训练速度显著提升
- 在保持高质量生成的同时，大幅减少训练耗时，适合快速实验
基于分数或扩散模型的表格数据生成方法能生成高质量数据，优于基于GAN和VAE的方法，但训练时间长。本文提出RecTable，采用修正流建模技术，该技术已在文本到图像、文本到视频生成中应用。RecTable具有简单架构，仅由若干堆叠的门控线性单元块构成。同时，其训练策略也简洁，包含混合类型噪声分布和对数正态时间步分布。实验表明，RecTable在性能上可媲美多个最先进的扩散与分数模型，同时显著降低训练时间。代码已开源：https://github.com/fmp453/rectable。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。