从对齐视角统一修正反向传播归因中的令人困惑行为
Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective
AI总结：
针对修正BP归因缺乏理论解释且存在异常行为的问题，本文提出统一框架证明GBP、RectGrad、LRP和DTD通过激活神经元权重实现输入对齐，从而解释并预测其行为。
摘要：
归因旨在识别与决策过程相关的输入像素。一种流行方法是使用修正反向传播（BP）规则来反转决策，与原始梯度相比提升了可解释性。然而，这些方法缺乏坚实的理论基础，并表现出令人困惑的行为，例如对参数随机化的敏感性降低，这引发了对其可靠性的担忧，并凸显了理论论证的必要性。在本工作中，我们为 GBP、RectGrad、LRP 和 DTD 等方法提出了一个统一理论框架，证明它们通过组合激活神经元的权重来实现输入对齐。这种对齐提升了可视化质量，并降低了对权重随机化的敏感性。我们的贡献包括：（1）为多种行为提供统一解释，而非仅关注单一行为。（2）准确预测新的行为。（3）为决策过程提供洞见，包括逐层信息变化以及归因与模型决策之间的关系。
英文摘要：
Attributions aim to identify input pixels that are relevant to the decision-making process. A popular approach involves using modified backpropagation (BP) rules to reverse decisions, which improves interpretability compared to the original gradients. However, these methods lack a solid theoretical foundation and exhibit perplexing behaviors, such as reduced sensitivity to parameter randomization, raising concerns about their reliability and highlighting the need for theoretical justification. In this work, we present a unified theoretical framework for methods like GBP, RectGrad, LRP, and DTD, demonstrating that they achieve input alignment by combining the weights of activated neurons. This alignment improves the visualization quality and reduces sensitivity to weight randomization. Our contributions include: (1) Providing a unified explanation for multiple behaviors, rather than focusing on just one. (2) Accurately predicting novel behaviors. (3) Offering insights into decision-making processes, including layer-wise information changes and the relationship between attributions and model decisions.
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。
