提出级联流匹配方法，更好生成混合类型表格数据。
Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features
- 分两步生成：先粗略生成类别特征，再精细重构数值特征
- 检测得分提升51.9%，更准确捕捉分布细节
- 适合需要真实表格数据生成的科研与工业场景
生成模型在包含离散与连续特征的表格数据上取得进展，但如何生成兼具离散状态与连续分布的混合类型特征仍具挑战。本文提出级联流匹配方法，先生成仅含类别特征及数值特征粗粒度表示的低分辨率样本，再通过新型条件概率路径和数据相关耦合，在高分辨率流匹配模型中利用该信息。低分辨率数值特征显式建模缺失值、异常值等离散结果，从而实现更真实的混合类型特征生成。我们形式化证明该级联结构可收紧传输代价界。实验表明，本模型生成样本更真实，分布细节捕捉更准确，例如检测得分提升51.9%。代码已开源：https://github.com/muellermarkus/tabcascade。
原文摘要 · Abstract (English)
Advances in generative modeling have recently been adapted to tabular data containing discrete and continuous features. However, generating mixed-type features that combine discrete states with an otherwise continuous distribution in a single feature remains challenging. We advance the state-of-the-art in diffusion models for tabular data with a cascaded approach. We first generate a low-resolution version of a tabular data row, that is, the collection of the purely categorical features and a coarse categorical representation of numerical features. Next, this information is leveraged in the high-resolution flow matching model via a novel guided conditional probability path and data-dependent coupling. The low-resolution representation of numerical features explicitly accounts for discrete outcomes, such as missing or inflated values, and therewith enables a more faithful generation of mixed-type features. We formally prove that this cascade tightens the transport cost bound. The results indicate that our model generates significantly more realistic samples and captures distributional details more accurately, for example, the detection score improves by 51.9\%. Code is available at https://github.com/muellermarkus/tabcascade.
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。