论文标题
解释深度学习中的本地，全球和高阶互动
Explaining Local, Global, And Higher-Order Interactions In Deep Learning
论文作者
论文摘要
我们提出了一种简单但高度可推广的方法，用于解释神经网络推理过程中的相互作用部分。首先，我们设计了一种基于跨导数的算法，用于计算单个特征之间的统计相互作用效应，该算法均被概括为2向和高阶和高阶（3路或更多）相互作用。我们与基于权重的归因技术并排提出结果，证实了交叉衍生物是2路和高阶相互作用检测的优越度量。此外，我们通过扩大基于流行的基于梯度的CNN的解释性工具的Grad-CAM将使用跨衍生物作为神经网络中的解释性设备的使用将其扩展到计算机视觉设置。尽管Grad-CAM只能解释单个对象在图像中的重要性，但我们称为Taylor-CAM的方法可以解释神经网络跨多个对象的关系推理。我们在定性和定量上都展示了我们的解释的成功，包括用户研究。我们将发布所有代码作为工具包，以促进可解释的深度学习。
We present a simple yet highly generalizable method for explaining interacting parts within a neural network's reasoning process. First, we design an algorithm based on cross derivatives for computing statistical interaction effects between individual features, which is generalized to both 2-way and higher-order (3-way or more) interactions. We present results side by side with a weight-based attribution technique, corroborating that cross derivatives are a superior metric for both 2-way and higher-order interaction detection. Moreover, we extend the use of cross derivatives as an explanatory device in neural networks to the computer vision setting by expanding Grad-CAM, a popular gradient-based explanatory tool for CNNs, to the higher order. While Grad-CAM can only explain the importance of individual objects in images, our method, which we call Taylor-CAM, can explain a neural network's relational reasoning across multiple objects. We show the success of our explanations both qualitatively and quantitatively, including with a user study. We will release all code as a tool package to facilitate explainable deep learning.
