融合局部解释生成完整可信的全局规则，提升可解释性与效率
CFIRE: A General Method for Combining Local Explanations
- 结合局部解释与闭频繁项集挖掘，生成全局决策规则
- 在14个数据集700个模型上表现稳定，精度与F1均提升
- 适用于多种解释器，解决方法不一致问题，适合实际部署
我们提出一种新型可解释人工智能算法，通过结合XAI方法与闭频繁项集挖掘，从表格数据的局部解释中生成忠实、易懂且完整的全局决策规则。该方法可兼容任意能标识特定样本重要特征的局部解释器，从而在不同模型与数据集间灵活选择最优解释器，缓解解释方法间的分歧问题。不同于常规评估方法，我们的实验还考虑了模型可解释性中的Rashomon效应。结果表明，该方法在所研究的14个基准数据集上的700个黑箱模型中均能有效找到合适规则，同时具备更优运行速度、高精度和高F1值，并生成紧凑完整的规则。
原文摘要 · Abstract (English)
We propose a novel eXplainable AI algorithm to compute faithful, easy-to-understand, and complete global decision rules from local explanations for tabular data by combining XAI methods with closed frequent itemset mining. Our method can be used with any local explainer that indicates which dimensions are important for a given sample for a given black-box decision. This property allows our algorithm to choose among different local explainers, addressing the disagreement problem, \ie the observation that no single explanation method consistently outperforms others across models and datasets. Unlike usual experimental methodology, our evaluation also accounts for the Rashomon effect in model explainability. To this end, we demonstrate the robustness of our approach in finding suitable rules for nearly all of the 700 black-box models we considered across 14 benchmark datasets. The results also show that our method exhibits improved runtime, high precision and F1-score while generating compact and complete rules.
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。