arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.09078cs.LG
收藏

探索GNN解释者--对GNN解释方法的严格理论和实证分析

Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods

Harvard University(哈佛大学)

Chirag Agarwal, Marinka Zitnik, Himabindu Lakkaraju

摘要:

随着图神经网络(GNN)越来越多地用于关键的现实世界应用,最近的文献中提出了几种方法来解释这些模型的预测。然而,几乎没有系统地分析这些方法的可靠性的工作。在这里,我们介绍了有史以来第一次对最先进的GNN解释方法的可靠性进行理论分析。更具体地说,我们从理论上分析了各种最先进的GNN解释方法相对于几个理想属性的行为(例如,忠诚、稳定和公平维护),并建立对这些属性的侵犯的上限。我们还使用九个真实世界的图形数据集进行了大量的实验,以经验验证了我们的理论结果。我们的实证结果进一步揭示了关于最先进GNN解释方法行为的几个有趣的见解。

英文摘要:

As Graph Neural Networks (GNNs) are increasingly being employed in critical real-world applications, several methods have been proposed in recent literature to explain the predictions of these models. However, there has been little to no work on systematically analyzing the reliability of these methods. Here, we introduce the first-ever theoretical analysis of the reliability of state-of-the-art GNN explanation methods. More specifically, we theoretically analyze the behavior of various state-of-the-art GNN explanation methods with respect to several desirable properties (e.g., faithfulness, stability, and fairness preservation) and establish upper bounds on the violation of these properties. We also empirically validate our theoretical results using extensive experimentation with nine real-world graph datasets. Our empirical results further shed light on several interesting insights about the behavior of state-of-the-art GNN explanation 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。

↑