Wen Yanhong, Li Yuhua, Zou Yixiong, Shu Kai, Chen Han, Zhao Ziwen, Ye Jinxian, Fu Quan, Li Ruixuan
School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China; Institute of Artificial Intelligence, Huazhong University of Science and Technology, Wuhan, China.
School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China.
Neural Netw. 2025 Oct;190:107645. doi: 10.1016/j.neunet.2025.107645. Epub 2025 Jun 3.
Most existing research on the interpretability of Graph Neural Networks (GNNs) for Link Prediction (LP) focuses on homogeneous graphs, with relatively few studies on heterogeneous graphs. Community is a crucial structure of a graph and can often improve LP performance. However, existing GNN explanation methods for heterogeneous LP rarely consider the impact of communities, leading to generated explanations that do not align with human understanding. To fill this gap, we consider community influence in GNN explanation for heterogeneous LP. We first demonstrate the effectiveness of communities in GNN explanations for heterogeneous LP through a preliminary analysis. Under this premise, we propose CI-Path, a Community-Influencing Path explanation for heterogeneous GNN-based LP that considers the influence of communities throughout the entire learning process. Specifically, we conduct degree centrality pruning and employ a community detection algorithm for data preprocessing. Then we propose a community-influencing objective, comprising community-influencing prediction loss and community-influencing path loss. Finally, we identify the reasonable explanatory paths that are the shortest with the minimum sum of node degrees and the fewest number of communities crossed. Extensive experiments on five heterogeneous datasets demonstrate the superior performance of CI-Path compared to baselines. Our code is available at https://github.com/wenyhsmile/CI-Path.
大多数现有的关于图神经网络（GNN）用于链路预测（LP）的可解释性研究都集中在同构图上，而异构图的相关研究相对较少。社区是图的一个关键结构，通常可以提高LP性能。然而，现有的用于异质LP的GNN解释方法很少考虑社区的影响，导致生成的解释与人类理解不一致。为了填补这一空白，我们在GNN对异质LP的解释中考虑社区影响。我们首先通过初步分析证明了社区在GNN对异质LP的解释中的有效性。在此前提下，我们提出了CI-Path，一种基于社区影响路径的解释方法，用于基于异质GNN的LP，该方法在整个学习过程中考虑了社区的影响。具体来说，我们进行度中心性剪枝，并采用社区检测算法进行数据预处理。然后我们提出了一个社区影响目标，包括社区影响预测损失和社区影响路径损失。最后，我们确定了合理的解释路径，这些路径是最短的，节点度之和最小，并且跨越的社区数量最少。在五个异质数据集上进行的大量实验表明，CI-Path相对于基线具有优越的性能。我们的代码可在https://github.com/wenyhsmile/CI-Path获取。
