We formulate an XAI-based model improvement approach for Graph Neural
Networks (GNNs) for node classification, called Explanation Enhanced Graph
Learning (EEGL). The goal is to improve predictive performance of GNN using
explanations. EEGL is an iterative self-improving algorithm, which starts with
a learned "vanilla" GNN, and repeatedly uses frequent subgraph mining to find
relevant patterns in explanation subgraphs. These patterns are then filtered
further to obtain application-dependent features corresponding to the presence
of certain subgraphs in the node neighborhoods. Giving an application-dependent
algorithm for such a subgraph-based extension of the Weisfeiler-Leman (1-WL)
algorithm has previously been posed as an open problem. We present experimental
evidence, with synthetic and real-world data, which show that EEGL outperforms
related approaches in predictive performance and that it has a
node-distinguishing power beyond that of vanilla GNNs. We also analyze EEGL's
training dynamics.

我们提出了一种基于可解释人工智能的模型改进方法，名为 Explanation Enhanced Graph Learning (EEGL)，旨在通过解释来提高图神经网络（GNN）在节点分类中的预测性能。EEGL 是一个迭代的自我改进算法，通过频繁子图挖掘来寻找解释子图中的相关模式，并进一步过滤以获得与节点邻域中特定子图的存在对应的应用相关特征。我们提供了针对这种基于子图的 Weisfeiler-Leman（1-WL）算法扩展的应用相关算法，并通过合成和真实世界数据的实验证据表明，EEGL 在预测性能方面优于相关方法，并具有超越普通 GNN 的节点区分能力。我们还分析了 EEGL 的训练动态。