通过最大化解释方向与流形切空间对齐，提升神经网络解释的可读性。
Tangentially Aligned Integrated Gradients for User-Friendly Explanations
- 基于流形切空间对齐优化基点选择，使解释更符合数据内在结构
- 在多个图像分类数据集上验证，最优基点可显著改善解释一致性
- 适合关注模型可解释性、尤其是视觉任务的科研与工程人员
集成梯度是解决神经网络黑箱问题的常用方法。其解释结果依赖于基点的选择，而基点选择不明确可能导致截然不同的解释。已有假设认为数据位于低维黎曼流形上，解释质量可通过其是否落在某点的切空间来衡量。本文提出应选择使解释方向与切空间对齐程度最大的基点。我们形式化了切向对齐的概念，并给出理论条件以确保解释位于切空间内。我们在多个知名图像分类数据集上展示了如何近似求解最优基点。此外，将该方法与常见基点及三种梯度可解释性模型进行对比，验证了其优越性。
原文摘要 · Abstract (English)
Integrated gradients is prevalent within machine learning to address the black-box problem of neural networks. The explanations given by integrated gradients depend on a choice of base-point. The choice of base-point is not a priori obvious and can lead to drastically different explanations. There is a longstanding hypothesis that data lies on a low dimensional Riemannian manifold. The quality of explanations on a manifold can be measured by the extent to which an explanation for a point lies in its tangent space. In this work, we propose that the base-point should be chosen such that it maximises the tangential alignment of the explanation. We formalise the notion of tangential alignment and provide theoretical conditions under which a base-point choice will provide explanations lying in the tangent space. We demonstrate how to approximate the optimal base-point on several well-known image classification datasets. Furthermore, we compare the optimal base-point choice with common base-points and three gradient explainability models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。