用扩散模型处理连续变量，实现异构表格数据的灵活生成。
Diffusion-nested Auto-Regressive Synthesis of Heterogeneous Tabular Data
- 用扩散模型参数化连续特征条件分布，适配异构表格数据。
- 采用双向掩码变换器，支持任意列生成顺序，提升灵活性。
- 在10个数据集上比现有方法提升18%~45%，适合生成任务场景。
自回归模型在自然语言生成中占主导地位，但在表格数据生成中应用有限。原因在于：1）表格数据包含异构数据类型，而自回归模型主要针对离散值设计；2）表格数据列顺序不变，需支持任意生成顺序。本文提出扩散嵌套自回归模型（TabDAR），解决上述问题。为处理连续列，TabDAR采用扩散模型参数化连续特征的条件分布；为支持任意生成顺序，引入带双向注意力的掩码变换器，模拟不同列序组合，从而学习目标列给定其他列的条件分布。该设计使TabDAR可自由处理异构表格数据，并支持便捷的无条件/有条件采样。在10个具有不同特性的数据集上进行实验，所提方法在8项指标上比先前最优方法提升18%至45%，覆盖三个不同方面。
原文摘要 · Abstract (English)
Autoregressive models are predominant in natural language generation, while their application in tabular data remains underexplored. We posit that this can be attributed to two factors: 1) tabular data contains heterogeneous data type, while the autoregressive model is primarily designed to model discrete-valued data; 2) tabular data is column permutation-invariant, requiring a generation model to generate columns in arbitrary order. This paper proposes a Diffusion-nested Autoregressive model (TabDAR) to address these issues. To enable autoregressive methods for continuous columns, TabDAR employs a diffusion model to parameterize the conditional distribution of continuous features. To ensure arbitrary generation order, TabDAR resorts to masked transformers with bi-directional attention, which simulate various permutations of column order, hence enabling it to learn the conditional distribution of a target column given an arbitrary combination of other columns. These designs enable TabDAR to not only freely handle heterogeneous tabular data but also support convenient and flexible unconditional/conditional sampling. We conduct extensive experiments on ten datasets with distinct properties, and the proposed TabDAR outperforms previous state-of-the-art methods by 18% to 45% on eight metrics across three distinct aspects.
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。