arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.09258cs.LGcs.AI
收藏

图神经网络的可解释性:实验研究

Explainability in Graph Neural Networks: An Experimental Survey

University of New South Wales(新南威尔士大学)

Peibo Li, Yixing Yang, Maurice Pagnucco, Yang Song

摘要:

图神经网络(GNNs)已经在各种应用领域中被广泛地开发用于图表示学习。然而,与所有其他神经网络模型类似,GNN也存在黑箱问题,因为人们无法理解其背后的机制。为了解决这个问题,已经提出了几种GNN可解释性方法来解释GNN做出的决策。在这次调查中,我们概述了最先进的GNN可解释性方法以及如何评估它们。此外,我们提出了一个新的评估指标,并进行了彻底的实验,比较GNN的可解释性方法在现实世界的数据集。我们还提出了GNN可解释性的未来方向。

英文摘要:

Graph neural networks (GNNs) have been extensively developed for graph representation learning in various application domains. However, similar to all other neural networks models, GNNs suffer from the black-box problem as people cannot understand the mechanism underlying them. To solve this problem, several GNN explainability methods have been proposed to explain the decisions made by GNNs. In this survey, we give an overview of the state-of-the-art GNN explainability methods and how they are evaluated. Furthermore, we propose a new evaluation metric and conduct thorough experiments to compare GNN explainability methods on real world datasets. We also suggest future directions for GNN explainability.

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。

↑