Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score using modified rules, rather than the gradient. We analyze an extensive set of modified BP methods: Deep Taylor Decomposition, Layer-wise Relevance Propagation (LRP), Excitation BP, PatternAttribution, DeepLIFT, Deconv, RectGrad, and Guided BP. We find empirically that the explanations of all mentioned methods, except for DeepLIFT, are independent of the parameters of later layers. We provide theoretical insights for this surprising behavior and also analyze why DeepLIFT does not suffer from this limitation. Empirically, we measure how information of later layers is ignored by using our new metric, cosine similarity convergence (CSC). The paper provides a framework to assess the faithfulness of new and existing modified BP methods theoretically and empirically. For code see: https://github.com/berleon/when-explanations-lie

翻译：归因方法旨在通过突出显示最相关的图像区域来解释神经网络的预测。一种常见的方法是使用修改后的规则（而非梯度）反向传播自定义的相关性分数。我们分析了一系列修改后的反向传播方法：深度泰勒分解、逐层相关性传播、激发反向传播、模式归因、DeepLIFT、反卷积、RectGrad和引导反向传播。我们通过实验发现，除DeepLIFT外，所有提及方法的解释均与后续层的参数无关。我们为这种令人惊讶的行为提供了理论见解，并分析了DeepLIFT为何不受此限制。通过使用我们的新度量——余弦相似度收敛（CSC），我们实验测量了后续层信息被忽略的程度。本文为从理论和实验角度评估新的及现有的修改后反向传播方法的忠实性提供了一个框架。代码参见：https://github.com/berleon/when-explanations-lie