On Explainability of Graph Neural Networks via Subgraph Explorations
On Explainability of Graph Neural Networks via Subgraph Explorations
复制标题
DOI：
--
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
Hao Yuan;Haiyang Yu;Jie Wang;Kang Li;Shuiwang Ji
中科院分区：
文献类型：
--
作者：
Hao Yuan;Haiyang Yu;Jie Wang;Kang Li;Shuiwang Ji
我们考虑了解释图神经网络(GNN)的预测的问题，否则它被认为是黑盒。现有的方法总是侧重于解释图的节点或边的重要性，而忽略了图的子结构，因为图的子结构更直观，更容易被人类理解。在这项工作中，我们提出了一种新的方法，称为Subgraph X，通过识别重要的子图来解释GNN。给定一个训练好的GNN模型和一个输入图，我们的Subgraph X通过使用蒙特卡罗树搜索有效地探索不同的子图来解释其预测。为了使树搜索更有效，我们提出使用Shapley值作为子图重要性的度量，它还可以捕捉不同子图之间的交互。为了加快计算速度，我们提出了有效的近似方案来计算图数据的Shapley值。我们的工作是首次尝试通过显式和直接地识别子图来解释GNN。实验结果表明，我们的Subgraph X在将计算保持在合理水平的同时，显著改善了解释。
We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explaining the importance of graph nodes or edges but ignore the substructures of graphs, which are more intuitive and human-intelligible. In this work, we propose a novel method, known as SubgraphX, to explain GNNs by identifying important subgraphs. Given a trained GNN model and an input graph, our SubgraphX explains its predictions by efficiently exploring different subgraphs with Monte Carlo tree search. To make the tree search more effective, we propose to use Shapley values as a measure of subgraph importance, which can also capture the interactions among different subgraphs. To expedite computations, we propose efficient approximation schemes to compute Shapley values for graph data. Our work represents the first attempt to explain GNNs via identifying subgraphs explicitly and directly. Experimental results show that our SubgraphX achieves significantly improved explanations, while keeping computations at a reasonable level.