Understanding and explaining the predictions of Graph Neural Networks (GNNs), is crucial for enhancing their safety and trustworthiness. Subgraph-level explanations are gaining attention for their intuitive appeal. However, most existing subgraph-level explainers face efficiency challenges in explaining GNNs due to complex search processes. The key challenge is to find a balance between intuitiveness and efficiency while ensuring transparency. Additionally, these explainers usually induce subgraphs by nodes, which may introduce less-intuitive disconnected nodes in the subgraph-level explanations or omit many important subgraph structures. In this paper, we reveal that inducing subgraph explanations by edges is more comprehensive than other subgraph inducing techniques. We also emphasize the need of determining the subgraph explanation size for each data instance, as different data instances may involve different important substructures. Building upon these considerations, we introduce a training-free approach, named EiG-Search. We employ an efficient linear-time search algorithm over the edge-induced subgraphs, where the edges are ranked by an enhanced gradient-based importance. We conduct extensive experiments on a total of seven datasets, demonstrating its superior performance and efficiency both quantitatively and qualitatively over the leading baselines.

翻译：理解和解释图神经网络（GNN）的预测结果，对于提升其安全性和可信度至关重要。子图级别的解释因其直观性而日益受到关注。然而，现有的大多数子图级解释器因复杂的搜索过程，在解释GNN时面临效率挑战。关键问题在于如何在保证透明性的前提下，找到直观性与效率之间的平衡。此外，这些解释器通常通过节点来诱导子图，可能导致子图级解释中包含不直观的不连通节点，或遗漏许多重要的子图结构。本文揭示，通过边诱导子图解释比其他子图诱导技术更为全面。我们还强调，需要为每个数据实例确定子图解释的规模，因为不同数据实例可能涉及不同的重要子结构。基于这些考量，我们提出了一种无需训练的方法，名为EiG-Search。我们对边诱导子图采用高效的线性时间搜索算法，其中边依据增强的梯度重要性进行排序。我们在共计七个数据集上开展了广泛实验，从定量和定性两个角度证明了该方法相对于主流基线在性能和效率上的优越性。