Subgraph-enhanced graph neural networks (SGNN) can increase the expressive power of the standard message-passing framework. This model family represents each graph as a collection of subgraphs, generally extracted by random sampling or with hand-crafted heuristics. Our key observation is that by selecting "meaningful" subgraphs, besides improving the expressivity of a GNN, it is also possible to obtain interpretable results. For this purpose, we introduce a novel framework that jointly predicts the class of the graph and a set of explanatory sparse subgraphs, which can be analyzed to understand the decision process of the classifier. We compare the performance of our framework against standard subgraph extraction policies, like random node/edge deletion strategies. The subgraphs produced by our framework allow to achieve comparable performance in terms of accuracy, with the additional benefit of providing explanations.

翻译：子图增强型图神经网络（SGNN）能够提升标准消息传递框架的表达能力。该模型系列将每个图表示为子图集合，通常通过随机采样或手工设计的启发式方法提取。我们的关键发现是：通过选取"有意义的"子图，除了能增强GNN的表达力，还能获得可解释的结果。为此，我们提出一种新型框架，可同时预测图类别并生成一组可解释的稀疏子图，通过分析这些子图能够理解分类器的决策过程。我们将所提框架与标准子图提取策略（如随机节点/边删除策略）进行性能对比。实验表明，我们的框架生成的子图在准确率方面可达到可比性能，同时具备提供解释的额外优势。