An Explainer for Temporal Graph Neural Networks
An Explainer for Temporal Graph Neural Networks
复制标题
DOI：
10.1109/globecom48099.2022.10001619
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
Wenchong He;Minh N. Vu;Zhe Jiang;M. Thai
中科院分区：
文献类型：
--
作者：
Wenchong He;Minh N. Vu;Zhe Jiang;M. Thai
时态图神经网络（TGNN）由于能够捕获图拓扑依赖性和非线性时态动态而被广泛用于对时间演化图相关任务进行建模。 TGNN 的解释对于透明且值得信赖的模型至关重要。然而，复杂的拓扑结构和时间依赖性使得解释 TGNN 模型非常具有挑战性。在本文中，我们提出了一种新颖的 TGNN 模型解释器框架。给定要解释的图表上的时间序列，该框架可以在一段时间内以概率图模型的形式识别主要解释。交通领域的案例研究表明，所提出的方法可以发现一段时间内道路网络中的动态依赖结构。
Temporal graph neural networks (TGNNs) have been widely used for modeling time-evolving graph-related tasks due to their ability to capture both graph topology dependency and non-linear temporal dynamic. The explanation of TGNNs is of vital importance for a transparent and trustworthy model. However, the complex topology structure and temporal depen-dency make explaining TGNN models very challenging. In this paper, we propose a novel explainer framework for TGNN models. Given a time series on a graph to be explained, the framework can identify dominant explanations in the form of a probabilistic graphical model in a time period. Case studies on the transportation domain demonstrate that the proposed approach can discover dynamic dependency structures in a road network for a time period.