In this work, we instantiate a novel perturbation-based multi-class
explanation framework, LIPEx (Locally Interpretable Probabilistic Explanation).
We demonstrate that LIPEx not only locally replicates the probability
distributions output by the widely used complex classification models but also
provides insight into how every feature deemed to be important affects the
prediction probability for each of the possible classes. We achieve this by
defining the explanation as a matrix obtained via regression with respect to
the Hellinger distance in the space of probability distributions. Ablation
tests on text and image data, show that LIPEx-guided removal of important
features from the data causes more change in predictions for the underlying
model than similar tests on other saliency-based or feature importance-based
XAI methods. It is also shown that compared to LIME, LIPEx is much more data
efficient in terms of the number of perturbations needed for reliable
evaluation of the explanation.

本研究介绍了一种新型的基于扰动的多类别解释框架 LIPEx（局部可解释的概率解释），证明 LIPEx 不仅可以局部复制广泛使用的复杂分类模型输出的概率分布，而且还可以提供关于每个被认为重要的特征如何影响每个可能类别的预测概率的见解。研究通过根据概率分布空间中的 Hellinger 距离执行的回归获得解释的矩阵。对文本和图像数据进行的消融测试表明，与其他基于显著性或特征重要性的 XAI 方法相比，LIPEx 指导下从数据中移除重要特征会对底层模型的预测产生更大的变化。研究还表明，与 LIME 相比，LIPEx 在可靠评估解释所需的扰动数量上具有更高的数据效率。