RecTable：使用修正流快速建模表格數據

RecTable: Fast Modeling Tabular Data with Rectified Flow

March 26, 2025

作者: Masane Fuchi, Tomohiro Takagi

cs.AI

摘要

基於分數或擴散模型生成高品質的表格數據，其表現超越了基於GAN和VAE的模型。然而，這些方法需要大量的訓練時間。本文介紹了RecTable，它採用了在文本到圖像生成和文本到視頻生成等領域中應用的修正流建模。RecTable具有簡單的架構，僅由幾個堆疊的門控線性單元塊組成。此外，我們的訓練策略也相當簡潔，結合了混合型噪聲分佈和對數正態時間步分佈。實驗結果顯示，RecTable在與多種最先進的擴散和基於分數的模型相比時，展現了競爭力的性能，同時大幅減少了所需的訓練時間。我們的代碼可在https://github.com/fmp453/rectable 獲取。

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.