用扩散模型生成真实可信的表格数据反事实解释。
Tabular Diffusion Counterfactual Explanations
- 基于改进的Gumbel-softmax近似，设计类别型特征的引导逆过程。
- 在多个信贷数据集上验证，解释结果更真实、多样且稳定。
- 适合金融与社会科学中需要可解释决策的场景。
反事实解释是可解释机器学习中的重要工具。近期进展多聚焦于计算机视觉领域的扩散模型解释方法，但对表格数据的应用较少。本文针对金融与社会科学中常见的表格数据，提出一种基于Gumbel-softmax分布近似的类别型特征引导逆过程。我们研究温度参数τ的影响，并推导出该近似分布与原分布之间的理论边界。在多个大规模信贷及其他表格数据集上进行实验，评估了可解释性、多样性、不稳定性与有效性等量化指标。结果表明，所提方法优于主流基线，在生成稳健且现实的反事实解释方面表现优异。
原文摘要 · Abstract (English)
Counterfactual explanations methods provide an important tool in the field of {interpretable machine learning}. Recent advances in this direction have focused on diffusion models to explain a deep classifier. However, these techniques have predominantly focused on problems in computer vision. In this paper, we focus on tabular data typical in finance and the social sciences and propose a novel guided reverse process for categorical features based on an approximation to the Gumbel-softmax distribution. Furthermore, we study the effect of the temperature $τ$ and derive a theoretical bound between the Gumbel-softmax distribution and our proposed approximated distribution. We perform experiments on several large-scale credit lending and other tabular datasets, assessing their performance in terms of the quantitative measures of interpretability, diversity, instability, and validity. These results indicate that our approach outperforms popular baseline methods, producing robust and realistic counterfactual explanations.
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。