更多的扰动，更多的陷阱：理解图神经网络的行为
Perturb More, Trap More: Understanding Behaviors of Graph Neural Networks
摘要：
虽然图神经网络（GNN）在图上的各种任务中显示出巨大的潜力，但缺乏透明度阻碍了理解GNN如何实现其预测。虽然GNN的解释很少，但忽略了对局部保真度的考虑，这表明应该预测模型在实例周围的行为。在本文中，我们首先提出了一种新的基于局部保真度的事后框架，用于任何训练的GNNs -TraP 2，它可以生成高保真的解释。考虑到需要突出每个节点内部的相关图结构和重要特征，TraP 2设计了一个三层架构：i）翻译层预先定义解释域; ii）扰动层探测和监控被解释GNN的局部预测行为，在解释域中对图结构和特征级进行多次扰动; iii）通过Paraphrase层拟合局部决策边界生成高可信度的解释。最后，在六个基准数据集上对TraP 2进行了评价，并从准确性、忠实性、决策性、洞察力和灵感五个方面对TraP 2进行了评价，结果表明，与现有方法相比，该方法具有$10.2\%$更高的解释准确性.
英文摘要：
While graph neural networks (GNNs) have shown a great potential in various tasks on graph, the lack of transparency has hindered understanding how GNNs arrived at its predictions. Although few explainers for GNNs are explored, the consideration of local fidelity, indicating how the model behaves around an instance should be predicted, is neglected. In this paper, we first propose a novel post-hoc framework based on local fidelity for any trained GNNs - TraP2, which can generate a high-fidelity explanation. Considering that both relevant graph structure and important features inside each node need to be highlighted, a three-layer architecture in TraP2 is designed: i) interpretation domain are defined by Translation layer in advance; ii) local predictive behavior of GNNs being explained are probed and monitored by Perturbation layer, in which multiple perturbations for graph structure and feature-level are conducted in interpretation domain; iii) high faithful explanations are generated by fitting the local decision boundary through Paraphrase layer. Finally, TraP2 is evaluated on six benchmark datasets based on five desired attributions: accuracy, fidelity, decisiveness, insight and inspiration, which achieves $10.2\%$ higher explanation accuracy than the state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
