论文标题
AI解释方法中的鲁棒性和实用性
Robustness and Usefulness in AI Explanation Methods
论文作者
论文摘要
随着机器学习驱动的系统变得无处不在，机器学习中的解释性变得非常重要，并且监管和公众情绪都开始要求了解这些系统如何做出决策。结果，许多解释方法已经开始得到广泛的采用。这项工作总结，比较和对比了三种流行的解释方法：石灰，光滑和摇摆。我们在样本复杂性和稳定性的意义上评估了这些方法：鲁棒性；从提供解释的意义上讲，可理解性与用户期望一致；从某种意义上说，解释允许根据输出修改模型。这项工作得出结论，当前的解释方法不足。实际上，信仰并采用这些方法可能比仅仅不使用它们更糟糕。
Explainability in machine learning has become incredibly important as machine learning-powered systems become ubiquitous and both regulation and public sentiment begin to demand an understanding of how these systems make decisions. As a result, a number of explanation methods have begun to receive widespread adoption. This work summarizes, compares, and contrasts three popular explanation methods: LIME, SmoothGrad, and SHAP. We evaluate these methods with respect to: robustness, in the sense of sample complexity and stability; understandability, in the sense that provided explanations are consistent with user expectations; and usability, in the sense that the explanations allow for the model to be modified based on the output. This work concludes that current explanation methods are insufficient; that putting faith in and adopting these methods may actually be worse than simply not using them.
