高效将神经网络转化为决策树：通往真实解释之路
摘要
尽管神经网络是强大的工具，但其广泛应用受到决策透明性和黑箱本质导致的可信度不足的制约。为缓解此问题，解释人工智能领域的方法试图揭示这些自动化决策的背后逻辑。但解释性人工智能方法常常存在忠实性/正确性缺失的问题，即有时提供的解释并不与神经网络的决策和逻辑一致。最近，一些转化为决策树的方法被提出来克服上述问题。然而，这些方法通常在神经网络规模增大时缺乏精确性、可扩展性或可解释性。因此，我们对这些先前结果进行了推广，尤其是考虑卷积神经网络、循环神经网络、非 ReLU 激活函数以及偏置项。我们的研究伴随严格的数学证明，我们提出了一种新算法 RENTT（Runtime Efficient Network to Tree Transformation），旨在以运行时和内存效率的方式计算神经网络的精确等价决策树表示。 resulting decision trees are multivariate and thus, possibly too complex to understand. To alleviate this problem, we also provide a method to calculate the ground truth feature importance for neural networks via the equivalent decision trees - for entire models (global), specific input regions (regional), or single decisions (local). All theoretical results are supported by detailed numerical experiments that emphasize two key aspects: the computational efficiency and scalability of our algorithm, and that only RENTT succeeds in uncovering ground truth explanations compared to conventional approximation methods like LIME and SHAP. All code is available at https://github.com/HelenaM23/RENTT。
引用
@article{arxiv.2511.09299,
title = {Efficiently Transforming Neural Networks into Decision Trees: A Path to Ground Truth Explanations with RENTT},
author = {Helena Monke and Benjamin Fresz and Marco Bernreuther and Yilin Chen and Marco F. Huber},
journal= {arXiv preprint arXiv:2511.09299},
year = {2025}
}