通过粒度球捕捉边的协同效应，提升图神经网络解释准确性
Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls
- 用可变大小的粒度球分解图，建模边间的协同作用
- 在结构图上扰动节点与边，生成更精准的解释子图
- 无需参数，适用于多种图分类任务
实例级解释旨在揭示图神经网络对特定图决策背后的依据。现有方法通过选择关键边构建子图来解释模型，通常通过扰动单个边并观察预测变化来评估边重要性。然而，这些方法常忽略边之间的协同效应，而这对于准确刻画边的重要性至关重要。为此，我们提出 SeeExplainer，一种无参数的 GNN 解释器。具体而言，我们引入粒度球图精炼机制，将图分解为若干不相交的、大小可变的粒度球，并以它们为节点构建结构图，从而更好地捕捉边间的协同效应。随后，在该结构图上扰动节点和边，基于其贡献生成解释性子图。在多个不同网络的图分类数据集上的实验表明，SeeExplainer 显著优于当前最优基线方法。
原文摘要 · Abstract (English)
Instance-level explanations aim to reveal the rationale behind a model's decisions for a specific graph. Previous methods explain graph neural networks (GNNs) by selecting important edges to induce subgraphs, where edge importance is assessed by perturbing each edge and observing changes in the model predictions. However, they often neglect the synergistic effects among edges, which are crucial for accurately characterizing edge importance. To address this issue, we propose SeeExplainer, a parameter-free explainer to interpret GNNs. Specifically, we first introduce a granular-ball graph refinement mechanism that decomposes a graph into several disjoint granular-balls with no fixed size, and utilize them as nodes to construct a structural graph. This process can better capture the synergistic effects among edges. Then, we perturb nodes and edges in the structural graph to generate explanatory subgraphs based on their respective contributions. Experiments on several graph classification datasets of different networks show that SeeExplainer outperforms state-of-the-art baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。