GNNBoundary: Towards Explaining Graph Neural Networks through the Lens of Decision Boundaries

While Graph Neural Networks (GNNs) have achieved remarkable performance on various machine learning tasks on graph data, they also raised questions regarding their transparency and interpretability. Recently, there have been extensive research efforts in explaining the decision-making process of GNNs. These efforts often focus on explaining why a certain prediction is being made for a particular instance, or what discriminative features the GNNs try to detect for each class. However, to the best of our knowledge, there is no existing study on understanding the decision boundaries of GNNs, even though the decision-making process of GNNs is directly determined by the decision boundaries. To bridge this research gap, we propose a model-level explainability method called GNNBoundary, which attempts to gain deeper insights into the decision boundaries of graph classifiers. Specifically, we first develop an algorithm to identify the pairs of classes whose decision regions are adjacent. For an adjacent class pair, the near-boundary graphs between them are effectively generated by optimizing a novel objective function specifically designed for the purpose of boundary graph generation. Thus, by analyzing the near-boundary graphs, the important characteristics of decision boundaries can be uncovered. To evaluate the efficacy of GNNBoundary, we conduct experiments on both synthetic datasets and public real-world datasets. The results have demonstrated that, through the analysis of faithful near-boundary graphs generated by GNNBoundary, we can thoroughly assess the robustness and generalizability of the explained GNNs.