While instance-level explanation of GNN is a well-studied problem with plenty of approaches being developed, providing a global explanation for the behaviour of a GNN is much less explored, despite its potential in interpretability and debugging. Existing solutions either simply list local explanations for a given class, or generate a synthetic prototypical graph with maximal score for a given class, completely missing any combinatorial aspect that the GNN could have learned. In this work, we propose GLGExplainer (Global Logic-based GNN Explainer), the first Global Explainer capable of generating explanations as arbitrary Boolean combinations of learned graphical concepts. GLGExplainer is a fully differentiable architecture that takes local explanations as inputs and combines them into a logic formula over graphical concepts, represented as clusters of local explanations. Contrary to existing solutions, GLGExplainer provides accurate and human-interpretable global explanations that are perfectly aligned with ground-truth explanations (on synthetic data) or match existing domain knowledge (on real-world data). Extracted formulas are faithful to the model predictions, to the point of providing insights into some occasionally incorrect rules learned by the model, making GLGExplainer a promising diagnostic tool for learned GNNs.
翻译:虽然对于GNN的实例级解释是一个广泛研究的问题, 但是对于GNN行为的全局解释却很少有相应的探索,尽管它在可解释性和调试方面具有潜在的作用。现有的解决方案要么仅仅列出给定类别的局部解释,要么生成一个具有给定类别最大分数的合成原型图,完全忽略了 GNN 可能学习到的组合特征。在本文中,我们提出了GLGExplainer(Global Logic-based GNN Explainer),这是一个全局解释器,能够通过学习到的图形概念的逻辑公式进行解释。GLGExplainer是一个完全可微的架构,将局部解释作为输入,并将它们组合成基于图形概念的逻辑公式,这些图形概念表示为局部解释的集群。与现有解决方案相反,GLGExplainer提供了准确且易于理解的全局解释,这些解释与基础真理解释完全一致(在合成数据方面)或与现有的领域知识相符(在真实数据方面)。提取的公式对于模型预测是可靠的,甚至可以提供一些由于某些偶然的学习规则错误而偏离准确结果的见解,使GLGExplainer成为了学习GNN的有前途的诊断工具。