用逻辑编程生成决策树的多种可解释性说明，适合高安全场景。
Formally Explaining Decision Tree Models with Answer Set Programming
- 基于答案集编程（ASP）构建可灵活编码偏好、枚举所有解释的方法。
- 在多个数据集上验证了对充分、对比、多数及树特异性解释的有效生成。
- 相比传统方法更易扩展，适合需要形式化论证的可信AI应用。
决策树模型（包括随机森林和梯度提升树）因预测性能优异而广泛使用，但其复杂结构常导致难以解释，尤其在安全关键场景中需形式化证明决策依据。本文提出一种基于答案集编程（ASP）的方法，可生成充分、对比、多数及树特异性等多类解释。相较于基于SAT的方法，本方法在编码用户偏好方面更具灵活性，并支持所有可能解释的枚举。我们在多样化的数据集上进行了实证评估，验证了该方法的有效性与局限性，表明其在可解释性生成上的优势。
原文摘要 · Abstract (English)
Decision tree models, including random forests and gradient-boosted decision trees, are widely used in machine learning due to their high predictive performance. However, their complex structures often make them difficult to interpret, especially in safety-critical applications where model decisions require formal justification. Recent work has demonstrated that logical and abductive explanations can be derived through automated reasoning techniques. In this paper, we propose a method for generating various types of explanations, namely, sufficient, contrastive, majority, and tree-specific explanations, using Answer Set Programming (ASP). Compared to SAT-based approaches, our ASP-based method offers greater flexibility in encoding user preferences and supports enumeration of all possible explanations. We empirically evaluate the approach on a diverse set of datasets and demonstrate its effectiveness and limitations compared to existing methods.
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。