用神经决策树提升LIME解释精度，让复杂模型更透明。
Enhancing LIME using Neural Decision Trees
- 用神经决策树替代传统线性或决策树做局部解释代理
- 在多个基准表格数据集上，解释保真度显著优于传统LIME
- 适合需要高精度局部解释的黑盒模型应用，如金融风控
解释复杂机器学习模型是重要挑战，尤其在表格数据中模型透明性尤为关键。局部可解释模型无关解释（LIME）是可解释机器学习中广泛使用的框架，也催生了诸多扩展。尽管传统LIME变体中使用的代理模型（如线性回归、决策树）具备一定稳定性，但难以准确捕捉许多复杂黑箱模型固有的非线性决策边界。本文致力于弥合高性能预测与可解释决策之间的差距。具体提出NDT-LIME，将神经决策树（NDTs）作为代理模型。通过利用NDTs的结构化层级特性，该方法旨在提供更准确、更有意义的局部解释。我们在多个基准表格数据集上评估其有效性，结果显示相较于传统LIME代理，解释保真度有持续提升。
原文摘要 · Abstract (English)
Interpreting complex machine learning models is a critical challenge, especially for tabular data where model transparency is paramount. Local Interpretable Model-Agnostic Explanations (LIME) has been a very popular framework for interpretable machine learning, also inspiring many extensions. While traditional surrogate models used in LIME variants (e.g. linear regression and decision trees) offer a degree of stability, they can struggle to faithfully capture the complex non-linear decision boundaries that are inherent in many sophisticated black-box models. This work contributes toward bridging the gap between high predictive performance and interpretable decision-making. Specifically, we propose the NDT-LIME variant that integrates Neural Decision Trees (NDTs) as surrogate models. By leveraging the structured, hierarchical nature of NDTs, our approach aims at providing more accurate and meaningful local explanations. We evaluate its effectiveness on several benchmark tabular datasets, showing consistent improvements in explanation fidelity over traditional LIME surrogates.
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。