Generating explanations for graph neural networks (GNNs) has been studied to understand their behavior in analytical tasks such as graph classification. Existing approaches aim to understand the overall results of GNNs rather than providing explanations for specific class labels of interest, and may return explanation structures that are hard to access, nor directly queryable. We propose GVEX, a novel paradigm that generates Graph Views for EXplanation. (1) We design a two-tier explanation structure called explanation views. An explanation view consists of a set of graph patterns and a set of induced explanation subgraphs. Given a database G of multiple graphs and a specific class label l assigned by a GNN-based classifier M, it concisely describes the fraction of G that best explains why l is assigned by M. (2) We propose quality measures and formulate an optimization problem to compute optimal explanation views for GNN explanation. We show that the problem is $\Sigma^2_P$-hard. (3) We present two algorithms. The first one follows an explain-and-summarize strategy that first generates high-quality explanation subgraphs which best explain GNNs in terms of feature influence maximization, and then performs a summarization step to generate patterns. We show that this strategy provides an approximation ratio of 1/2. Our second algorithm performs a single-pass to an input node stream in batches to incrementally maintain explanation views, having an anytime quality guarantee of 1/4 approximation. Using real-world benchmark data, we experimentally demonstrate the effectiveness, efficiency, and scalability of GVEX. Through case studies, we showcase the practical applications of GVEX.

翻译：为理解图神经网络（GNN）在图分类等分析任务中的行为，研究者已对其解释生成方法展开大量研究。现有方法侧重于理解GNN的整体结果，而非针对特定目标类别标签提供解释，且可能返回难以访问且无法直接查询的解释结构。我们提出GVEX——一种基于图视图（Graph Views）生成解释的新范式：(1) 设计名为"解释视图"的双层解释结构。每个解释视图由一组图模式与一组诱导解释子图构成。给定包含多个图的数据库G，以及基于GNN的分类器M分配的特定类别标签l，该结构可简洁描述G中能最有效解释M为何赋予标签l的子集；(2) 提出质量度量指标，并构建求解GNN解释最优解释视图的优化问题，证明该问题属$\Sigma^2_P$-难复杂度；(3) 提出两种算法：第一种采用"先解释后归纳"策略，首先生成基于特征影响最大化准则的最优解释子图以解释GNN行为，再通过归纳步骤生成图模式，该策略可实现1/2近似比；第二种算法对输入节点流进行单遍批处理以增量维护解释视图，具备1/4近似的即时质量保证。基于真实世界基准数据的实验验证了GVEX的有效性、效率与可扩展性，案例研究展示了其实际应用价值。