arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.02587cs.LGstat.ML
收藏

XGNN:面向图神经网络的模型级简化

XGNN: Towards Model-Level Explanations of Graph Neural Networks

Texas A&M University(德克萨斯农工大学);Michigan State University(密歇根州立大学)

Hao Yuan, Jiliang Tang, Xia Hu, Shuiwang Ji

摘要:

图神经网络(GNNs)通过聚集和组合邻居信息来学习节点特征,在许多图任务上取得了很好的性能。然而,GNN大多被视为黑箱,缺乏人类可理解的解释。因此,如果GNN模型无法解释,它们就不能完全信任并用于某些应用领域。在这项工作中,我们提出了一种新的方法,称为XGNN,在模型级解释GNN。我们的方法可以提供高层次的见解和对GNN如何工作的一般理解。特别是,我们建议通过训练图生成器来解释GNNs,以便生成的图模式最大化模型的某个预测。我们将图生成制定为强化学习任务,其中对于每一步,图生成器预测如何将边添加到当前图中。基于来自经训练的GNN的信息,经由策略梯度方法来训练图形生成器。此外,我们将几个图形规则,以鼓励生成的图形是有效的。在合成和真实世界数据集上的实验结果表明,我们提出的方法有助于理解和验证训练的GNN。此外,我们的实验结果表明,生成的图可以为如何改进训练的GNN提供指导。

英文摘要:

Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor information, which have achieved promising performance on many graph tasks. However, GNNs are mostly treated as black-boxes and lack human intelligible explanations. Thus, they cannot be fully trusted and used in certain application domains if GNN models cannot be explained. In this work, we propose a novel approach, known as XGNN, to interpret GNNs at the model-level. Our approach can provide high-level insights and generic understanding of how GNNs work. In particular, we propose to explain GNNs by training a graph generator so that the generated graph patterns maximize a certain prediction of the model.We formulate the graph generation as a reinforcement learning task, where for each step, the graph generator predicts how to add an edge into the current graph. The graph generator is trained via a policy gradient method based on information from the trained GNNs. In addition, we incorporate several graph rules to encourage the generated graphs to be valid. Experimental results on both synthetic and real-world datasets show that our proposed methods help understand and verify the trained GNNs. Furthermore, our experimental results indicate that the generated graphs can provide guidance on how to improve the trained GNNs.

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。

↑