论文标题
研究综合梯度中的饱和效应
Investigating Saturation Effects in Integrated Gradients
论文作者
论文摘要
综合梯度已成为事后模型可解释性的流行方法。 De-Spite它的受欢迎程度，整体路径不同区域的组成和相对影响尚不清楚。我们探索了这些效果，发现该路径饱和区域中的梯度在其中模型输出变化很小，对计算的归因不成比例。我们提出了一种集成量化的变体，该变体主要捕获不饱和区域中的梯度，并在成像网分类网络上评估该方法。我们发现，这种归因技术显示出更高的模型忠诚度，并且对噪声与标准综合梯度的敏感性更低。一本注释，说明了我们的计算和结果，请访问https://github.com/vivekmig/captum-1/tree/expandedig。
Integrated Gradients has become a popular method for post-hoc model interpretability. De-spite its popularity, the composition and relative impact of different regions of the integral path are not well understood. We explore these effects and find that gradients in saturated regions of this path, where model output changes minimally, contribute disproportionately to the computed attribution. We propose a variant of IntegratedGradients which primarily captures gradients in unsaturated regions and evaluate this method on ImageNet classification networks. We find that this attribution technique shows higher model faithfulness and lower sensitivity to noise com-pared with standard Integrated Gradients. A note-book illustrating our computations and results is available at https://github.com/vivekmig/captum-1/tree/ExpandedIG.
