Due to the absence of ground truth, objective evaluation of explainability
methods is an essential research direction. So far, the vast majority of
evaluations can be summarized into three categories, namely human evaluation,
sensitivity testing, and salinity check. This work proposes a novel evaluation
methodology from the perspective of generalizability. We employ an Autoencoder
to learn the distributions of the generated explanations and observe their
learnability as well as the plausibility of the learned distributional
features. We first briefly demonstrate the evaluation idea of the proposed
approach at LIME, and then quantitatively evaluate multiple popular
explainability methods. We also find that smoothing the explanations with
SmoothGrad can significantly enhance the generalizability of explanations.

本文提出了一种新的可解释性方法评估方法，从可泛化性的角度出发，使用自编码器学习生成解释的分布，并观察其可学性和学习分布特征的合理性；同时进行了 LIME 可解释性方法的直观演示，以及对多个流行可解释性方法的数量评估，并发现使用 SmoothGrad 来平滑解释可以显著增强解释的泛化性。

解释的普适性

The Generalizability of Explanations

As machine learning black boxes are increasingly being deployed in critical
domains such as healthcare and criminal justice, there has been a growing
emphasis on developing techniques for explaining these black boxes in a post
hoc manner. In this work, we analyze two popular post hoc interpretation
techniques: SmoothGrad which is a gradient based method, and a variant of LIME
which is a perturbation based method. More specifically, we derive explicit
closed form expressions for the explanations output by these two methods and
show that they both converge to the same explanation in expectation, i.e., when
the number of perturbed samples used by these methods is large. We then
leverage this connection to establish other desirable properties, such as
robustness, for these techniques. We also derive finite sample complexity
bounds for the number of perturbations required for these methods to converge
to their expected explanation. Finally, we empirically validate our theory
using extensive experimentation on both synthetic and real world datasets.

研究了两种流行的机器学习解释技术：基于梯度的 SmoothGrad 方法和一种基于扰动的 LIME 方法，并通过数学推导证明它们在期望上产生相同的解释。通过在合成和真实世界数据集上进行广泛实验验证了理论模型。

关于扰动和梯度解释的统一和鲁棒性

Towards the Unification and Robustness of Perturbation and Gradient  Based Explanations

Deep learning interpretation is essential to explain the reasoning behind
model predictions. Understanding the robustness of interpretation methods is
important especially in sensitive domains such as medical applications since
interpretation results are often used in downstream tasks. Although
gradient-based saliency maps are popular methods for deep learning
interpretation, recent works show that they can be vulnerable to adversarial
attacks. In this paper, we address this problem and provide a certifiable
defense method for deep learning interpretation. We show that a sparsified
version of the popular SmoothGrad method, which computes the average saliency
maps over random perturbations of the input, is certifiably robust against
adversarial perturbations. We obtain this result by extending recent bounds for
certifiably robust smooth classifiers to the interpretation setting.
Experiments on ImageNet samples validate our theory.

本研究提出了一种用于解释深度学习的可靠技术，并证实该方法对付对抗性攻击具有可靠性。

深度学习中的可证明鲁棒解释

Certifiably Robust Interpretation in Deep Learning

SmoothGrad and VarGrad are techniques that enhance the empirical quality of
standard saliency maps by adding noise to input. However, there were few works
that provide a rigorous theoretical interpretation of those methods. We
analytically formalize the result of these noise-adding methods. As a result,
we observe two interesting results from the existing noise-adding methods.
First, SmoothGrad does not make the gradient of the score function smooth.
Second, VarGrad is independent of the gradient of the score function. We
believe that our findings provide a clue to reveal the relationship between
local explanation methods of deep neural networks and higher-order partial
derivatives of the score function.

本文介绍了两种技术 SmoothGrad 和 VarGrad，这些技术通过添加噪声到输入来增强标准显著性图的经验质量，分析并阐述了这些噪声添加方法的严格理论解释，发现两种添加噪声的方法 SmoothGrad 并没有使得分数函数梯度平滑，VarGrad 与分数函数的梯度无关，从而为研究神经网络的本地解释方法和分数函数的高阶偏导数之间的关系提供了线索。