用Transformer-VAE生成表格数据的反事实解释，避免特征偏见。
TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAE
- 基于Transformer-VAE学习连续潜在空间，建模复杂表格特征关系。
- 在5个金融数据集上验证，无特征类型偏倚，生成效果优于现有方法。
- 适合需要公平、可解释决策的金融风控等场景。
在可解释人工智能（XAI）领域，反事实（CF）解释通过建议输入变化来改变模型预测，从而提供解释。在真实应用中，输入多为包含混合数据类型和复杂特征依赖关系的表格数据，这些特性难以建模，且我们实证发现会导致生成的反事实解释偏向特定特征类型。为此，本文提出TABCF，一种基于Transformer的变分自编码器（VAE）方法，专门用于建模表格数据。该方法利用Transformer学习连续潜在空间，并引入新型Gumbel-Softmax解码器，在保持端到端可微性的同时实现精确的分类变量重建。在五个金融数据集上的大量定量评估表明，TABCF不表现出对特定特征类型的偏倚，且生成的反事实解释在符合常见反事实期望方面优于现有方法。
原文摘要 · Abstract (English)
In the field of Explainable AI (XAI), counterfactual (CF) explanations are one prominent method to interpret a black-box model by suggesting changes to the input that would alter a prediction. In real-world applications, the input is predominantly in tabular form and comprised of mixed data types and complex feature interdependencies. These unique data characteristics are difficult to model, and we empirically show that they lead to bias towards specific feature types when generating CFs. To overcome this issue, we introduce TABCF, a CF explanation method that leverages a transformer-based Variational Autoencoder (VAE) tailored for modeling tabular data. Our approach uses transformers to learn a continuous latent space and a novel Gumbel-Softmax detokenizer that enables precise categorical reconstruction while preserving end-to-end differentiability. Extensive quantitative evaluation on five financial datasets demonstrates that TABCF does not exhibit bias toward specific feature types, and outperforms existing methods in producing effective CFs that align with common CF desiderata.
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。