论文标题
PGM-解释：图形神经网络的概率图形模型解释
PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
论文作者
论文摘要
在图神经网络（GNN）中，将图结构纳入了节点表示的学习中。这种复杂的结构使解释GNN的预测变得更加具有挑战性。在本文中，我们提出了PGM-解释器，这是GNNS的概率图形模型（PGM）模型 - 敏捷解释器。考虑到要解释的预测，PGM-解释器可以识别重要的图形组件，并以PGM的形式生成近似于该预测的PGM的解释。与现有的GNN解释器不同，该解释是从解释功能的一组线性函数中绘制的解释，PGM-解释器能够以条件概率的形式演示解释功能的依赖性。我们的理论分析表明，PGM-解释器生成的PGM包括目标预测的Markov-Blanket，即包括所有统计信息。我们还表明，PGM-解释器返回的解释在完美地图中包含相同的独立语句。我们对合成和现实世界数据集的实验表明，PGM-解释器的性能比许多基准任务中的现有解释器都更好。
In Graph Neural Networks (GNNs), the graph structure is incorporated into the learning of node representations. This complex structure makes explaining GNNs' predictions become much more challenging. In this paper, we propose PGM-Explainer, a Probabilistic Graphical Model (PGM) model-agnostic explainer for GNNs. Given a prediction to be explained, PGM-Explainer identifies crucial graph components and generates an explanation in form of a PGM approximating that prediction. Different from existing explainers for GNNs where the explanations are drawn from a set of linear functions of explained features, PGM-Explainer is able to demonstrate the dependencies of explained features in form of conditional probabilities. Our theoretical analysis shows that the PGM generated by PGM-Explainer includes the Markov-blanket of the target prediction, i.e. including all its statistical information. We also show that the explanation returned by PGM-Explainer contains the same set of independence statements in the perfect map. Our experiments on both synthetic and real-world datasets show that PGM-Explainer achieves better performance than existing explainers in many benchmark tasks.
