arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.00633cs.LG
收藏

关于图神经网络归因扰动评估之间差异的研究

On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions

Technical University of Munich(慕尼黑工业大学);Sharif University of Technology(谢里夫理工大学);Harvard Medical School(哈佛医学院);Hospital of the Ludwig-Maximilians-University (LMU) Munich(慕尼黑大学医院)

Razieh Rezaei, Alireza Dizaji, Ashkan Khakzar, Anees Kazi, Nassir Navab, Daniel Rueckert

AI总结:

本文从重新训练视角评估图神经网络归因方法,发现GNNExplainer等表现因数据集和网络而异,建议将重新训练评估作为特定场景的工具集而非通用基准。

摘要:

神经网络正越来越多地进入图领域并建模特征之间的关系。与此同时,图神经网络解释方法不断涌现,以揭示图节点之间的关系。然而,现有的归因方法之间存在差异,尚不清楚应该信任哪种归因。因此,研究引入了从不同视角评估它们的评估实验。在这项工作中,我们从图领域以前未探索过的视角评估归因方法:重新训练。核心思想是根据归因识别出的重要(或不重要)关系重新训练网络,并评估网络如何基于这些关系进行泛化。我们重新表述了重新训练框架,以规避先前表述中潜伏的问题,并提出了正确分析的指南。我们在四种最先进的GNN归因方法和五个合成及真实世界的图分类数据集上进行了分析。分析表明,归因的表现因数据集和网络而异。最重要的是,我们观察到著名的GNNExplainer的表现与对边缘重要性的任意指定相似。研究得出结论,重新训练评估不能用作通用基准,并建议将其作为工具集,用于在特定处理的网络、数据集和稀疏性上评估归因。

英文摘要:

Neural networks are increasingly finding their way into the realm of graphs and modeling relationships between features. Concurrently graph neural network explanation approaches are being invented to uncover relationships between the nodes of the graphs. However, there is a disparity between the existing attribution methods, and it is unclear which attribution to trust. Therefore research has introduced evaluation experiments that assess them from different perspectives. In this work, we assess attribution methods from a perspective not previously explored in the graph domain: retraining. The core idea is to retrain the network on important (or not important) relationships as identified by the attributions and evaluate how networks can generalize based on these relationships. We reformulate the retraining framework to sidestep issues lurking in the previous formulation and propose guidelines for correct analysis. We run our analysis on four state-of-the-art GNN attribution methods and five synthetic and real-world graph classification datasets. The analysis reveals that attributions perform variably depending on the dataset and the network. Most importantly, we observe that the famous GNNExplainer performs similarly to an arbitrary designation of edge importance. The study concludes that the retraining evaluation cannot be used as a generalized benchmark and recommends it as a toolset to evaluate attributions on a specifically addressed network, dataset, and sparsity.

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。

↑