使用反事实推断的因果生成解释器：以 Morpho-MNIST 数据集为例
Causal Generative Explainers using Counterfactual Inference: A Case Study on the Morpho-MNIST Dataset
AI总结：
本文利用因果生成学习与反事实推断，提出针对图像分类器的可解释方法，包括像素级影响分析、基于蒙特卡洛的属性重要性估计及反事实解释优化，并在 Morpho-MNIST 上验证其可解释性优于 OmnixAI。
摘要：
在本文中，我们提出利用因果生成学习作为解释图像分类器的可解释工具。具体而言，我们提出一种生成式反事实推断方法，通过生成学习研究视觉特征（即像素）以及因果因素的影响。为此，我们首先通过反事实推断改变因果属性的值，并针对具有这些不同属性值的反事实图像计算 Shapley 解释和对比解释，从而揭示对分类器决策最具影响力的像素。随后，我们利用因果生成模型的生成器建立一种蒙特卡洛机制，以适配 Shapley 解释器，使其在分类器仅基于数据集图像训练的情况下，能够为因果数据集中人类可解释的属性生成特征重要性。最后，我们提出通过反事实推断为分类器创建反事实解释的优化方法，并针对可微分类器和任意分类器分别给出直接的方法。我们利用 Morpho-MNIST 因果数据集作为案例研究，探索所提出的生成反事实解释的方法。我们采用 OmnixAI 开源工具包中的视觉解释方法与所提方法进行比较。通过采用定量指标衡量反事实解释的可解释性，我们发现所提出的反事实解释方法相比 OmnixAI 生成的方法能够提供更具可解释性的解释。这一发现表明，我们的方法非常适合在因果数据集上生成高度可解释的反事实解释。
英文摘要：
In this paper, we propose leveraging causal generative learning as an interpretable tool for explaining image classifiers. Specifically, we present a generative counterfactual inference approach to study the influence of visual features (i.e., pixels) as well as causal factors through generative learning. To this end, we first uncover the most influential pixels on a classifier's decision by varying the value of a causal attribute via counterfactual inference and computing both Shapely and contrastive explanations for counterfactual images with these different attribute values. We then establish a Monte-Carlo mechanism using the generator of a causal generative model in order to adapt Shapley explainers to produce feature importances for the human-interpretable attributes of a causal dataset in the case where a classifier has been trained exclusively on the images of the dataset. Finally, we present optimization methods for creating counterfactual explanations of classifiers by means of counterfactual inference, proposing straightforward approaches for both differentiable and arbitrary classifiers. We exploit the Morpho-MNIST causal dataset as a case study for exploring our proposed methods for generating counterfacutl explantions. We employ visual explanation methods from OmnixAI open source toolkit to compare them with our proposed methods. By employing quantitative metrics to measure the interpretability of counterfactual explanations, we find that our proposed methods of counterfactual explanation offer more interpretable explanations compared to those generated from OmnixAI. This finding suggests that our methods are well-suited for generating highly interpretable counterfactual explanations on causal datasets.
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。
