Understanding the decision-making process of Graph Neural Networks (GNNs) is crucial to their interpretability. Most existing methods for explaining GNNs typically rely on training auxiliary models, resulting in the explanations remain black-boxed. This paper introduces Graph Output Attribution (GOAt), a novel method to attribute graph outputs to input graph features, creating GNN explanations that are faithful, discriminative, as well as stable across similar samples. By expanding the GNN as a sum of scalar products involving node features, edge features and activation patterns, we propose an efficient analytical method to compute contribution of each node or edge feature to each scalar product and aggregate the contributions from all scalar products in the expansion form to derive the importance of each node and edge. Through extensive experiments on synthetic and real-world data, we show that our method not only outperforms various state-ofthe-art GNN explainers in terms of the commonly used fidelity metric, but also exhibits stronger discriminability, and stability by a remarkable margin.

翻译：理解图神经网络（GNN）的决策过程对其可解释性至关重要。现有的大多数GNN解释方法通常依赖于训练辅助模型，导致解释过程仍处于黑箱状态。本文提出图输出归因（GOAt）方法，这是一种将图输出归因于输入图特征的新方法，能够生成忠实、可区分且对相似样本保持稳定的GNN解释。通过将GNN展开为节点特征、边特征和激活模式标量积之和的形式，我们提出了一种高效的分析方法，用于计算每个节点或边特征对每个标量积的贡献，并聚合展开形式中所有标量积的贡献，从而推导出每个节点和边的重要性。通过在合成数据和真实数据上的大量实验表明，我们的方法不仅在常用保真度指标上优于多种最先进的GNN解释器，而且在可区分性和稳定性方面也展现出显著优势。