Explaining node predictions in graph neural networks (GNNs) often boils down to finding graph substructures that preserve predictions. Finding these structures usually implies back-propagating through the GNN, bonding the complexity (e.g., number of layers) of the GNN to the cost of explaining it. This naturally begs the question: Can we break this bond by explaining a simpler surrogate GNN? To answer the question, we propose Distill n' Explain (DnX). First, DnX learns a surrogate GNN via knowledge distillation. Then, DnX extracts node or edge-level explanations by solving a simple convex program. We also propose FastDnX, a faster version of DnX that leverages the linear decomposition of our surrogate model. Experiments show that DnX and FastDnX often outperform state-of-the-art GNN explainers while being orders of magnitude faster. Additionally, we support our empirical findings with theoretical results linking the quality of the surrogate model (i.e., distillation error) to the faithfulness of explanations.

翻译：解释图神经网络（GNN）中的节点预测通常归结为寻找保持预测结果的图子结构。寻找这些结构通常需要反向传播穿过GNN，从而将GNN的复杂性（如层数）与解释成本绑定。这自然引出一个问题：我们能否通过解释更简单的代理GNN来打破这种绑定？为回答该问题，我们提出Distill n' Explain（DnX）方法。首先，DnX通过知识蒸馏学习一个代理GNN。然后，DnX通过求解一个简单的凸规划来提取节点级或边级解释。我们还提出FastDnX，它是DnX的加速版本，利用了代理模型的线性分解特性。实验表明，DnX和FastDnX在多数情况下优于最先进的GNN解释器，同时速度快数个数量级。此外，我们通过理论结果支持实证发现，建立了代理模型质量（即蒸馏误差）与解释保真度之间的关联。