Local Universal Explainer (LUX)——一种具有事实、反事实和可视化解释的基于规则的解释器
Local Universal Explainer (LUX) -- a rule-based explainer with factual, counterfactual and visual explanations
AI总结：
本文提出基于规则的 LUX 解释器，利用斜向决策树、高密度真实数据簇与 SHAP 引导采样，统一生成事实、反事实和可视化解释，并在多数据集上优于现有方法。
摘要：
可解释人工智能（XAI）是近年来人工智能领域发展最为密集的方向之一。它同时也是最碎片化的领域之一，存在多种关注解释不同方面的方法。这使得人们难以以紧凑且一致的方式一次性获得完整的解释谱系。为解决这一问题，我们提出了 Local Universal Explainer (LUX)，这是一种基于规则的解释器，能够生成事实、反事实和可视化解释。它基于决策树算法的改进版本，允许斜向划分，并可与 SHAP 等特征重要性 XAI 方法集成。与其他算法相反，它限制数据生成的使用，而是专注于选择以真实数据高密度簇形式存在的局部概念，这些簇对形成被解释模型的决策边界影响最大，并通过新颖的 SHAP 引导采样算法生成人工样本。我们在真实和合成数据集上测试了该方法，并将其与 LORE、EXPLAN 和 Anchor 等最先进的基于规则的解释器进行比较。我们的方法在简洁性、保真度、代表性和一致性方面优于现有方法。
英文摘要：
Explainable artificial intelligence (XAI) is one of the most intensively developed area of AI in recent years. It is also one of the most fragmented with multiple methods that focus on different aspects of explanations. This makes difficult to obtain the full spectrum of explanation at once in a compact and consistent way. To address this issue, we present Local Universal Explainer (LUX), which is a rule-based explainer that can generate factual, counterfactual and visual explanations. It is based on a modified version of decision tree algorithms that allows for oblique splits and integration with feature importance XAI methods such as SHAP. It limits the use data generation in opposite to other algorithms, but is focused on selecting local concepts in a form of high-density clusters of real data that have the highest impact on forming the decision boundary of the explained model and generating artificial samples with novel SHAP-guided sampling algorithm. We tested our method on real and synthetic datasets and compared it with state-of-the-art rule-based explainers such as LORE, EXPLAN and Anchor. Our method outperforms the existing approaches in terms of simplicity, fidelity, representativeness, and consistency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
