AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing
AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing
复制标题
DOI：
10.48550/arxiv.2310.15479
复制
发表时间：
2023-10
期刊：
影响因子：
--
通讯作者：
Namjoon Suh;Xiaofeng Lin;Din-Yin Hsieh;Merhdad Honarkhah;Guang Cheng
中科院分区：
文献类型：
--
作者：
Namjoon Suh;Xiaofeng Lin;Din-Yin Hsieh;Merhdad Honarkhah;Guang Cheng
扩散模型已成为现代机器学习许多子场（包括计算机视觉，语言模型或语音综合）的合成数据生成的主要范式。在本文中，我们利用扩散模型的功能来生成合成表格数据。表格数据中的异质特征是表格数据综合的主要障碍，我们通过使用自动编码器体系结构来解决此问题。与最先进的表格合成器相比，我们模型的合成表显示了对真实数据的统计保真度，并且在机器学习公用事业的下游任务中表现良好。我们进行了超过$ 15 $的公开数据集的实验。值得注意的是，我们的模型擅长捕获特征之间的相关性，这在表格数据合成中一直是长期的挑战。我们的代码可从https://github.com/ucla-trustworthy-ai-lab/autodiffusion获得。
Diffusion model has become a main paradigm for synthetic data generation in many subfields of modern machine learning, including computer vision, language model, or speech synthesis. In this paper, we leverage the power of diffusion model for generating synthetic tabular data. The heterogeneous features in tabular data have been main obstacles in tabular data synthesis, and we tackle this problem by employing the auto-encoder architecture. When compared with the state-of-the-art tabular synthesizers, the resulting synthetic tables from our model show nice statistical fidelities to the real data, and perform well in downstream tasks for machine learning utilities. We conducted the experiments over $15$ publicly available datasets. Notably, our model adeptly captures the correlations among features, which has been a long-standing challenge in tabular data synthesis. Our code is available at https://github.com/UCLA-Trustworthy-AI-Lab/AutoDiffusion.