刻画 XAI 方法中相关特征的贡献
Characterizing the contribution of dependent features in XAI methods
AI总结:
针对 SHAP、LIME 等 XAI 方法错误假设预测变量独立的问题,本文提出一种模型无关的代理修正方法,以在共线性条件下刻画相关特征对模型的贡献。
摘要:
可解释人工智能(XAI)提供了一些工具,以帮助理解机器学习模型如何工作并得出特定结果。它有助于提高模型的可解释性,并使模型更可信、更透明。在这一背景下,许多 XAI 方法被提出,其中 SHAP 和 LIME 最为流行。然而,这些方法假设机器学习模型中使用的预测变量是相互独立的,而通常情况并不一定如此。这种假设给 XAI 结果(例如信息性预测变量列表)的稳健性蒙上了阴影。在此,我们提出了一种简单而有用的代理方法,用于修改任意 XAI 特征排序方法的输出,从而能够考虑预测变量之间的依赖关系。所提出的方法具有模型无关的优势,并且在存在共线性的情况下,能够简便地计算模型中每个预测变量的影响。
英文摘要:
Explainable Artificial Intelligence (XAI) provides tools to help understanding how the machine learning models work and reach a specific outcome. It helps to increase the interpretability of models and makes the models more trustworthy and transparent. In this context, many XAI methods were proposed being SHAP and LIME the most popular. However, the proposed methods assume that used predictors in the machine learning models are independent which in general is not necessarily true. Such assumption casts shadows on the robustness of the XAI outcomes such as the list of informative predictors. Here, we propose a simple, yet useful proxy that modifies the outcome of any XAI feature ranking method allowing to account for the dependency among the predictors. The proposed approach has the advantage of being model-agnostic as well as simple to calculate the impact of each predictor in the model in presence of collinearity.
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。