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 2312.05596cs.LG
收藏

图神经网络的因子化解释器

Factorized Explainer for Graph Neural Networks

Technical University of Munich(慕尼黑工业大学);Florida International University(佛罗里达国际大学)

Rundong Huang, Farhad Shirani, Dongsheng Luo

AI总结:

本文提出一种基于改进图信息瓶颈原理的因子化解释模型,用于避免常规GNN解释方法中的平凡解,并在合成及真实数据集上验证其有效性。

摘要:

图神经网络(GNNs)因其能够从图结构数据中学习而受到越来越多的关注。为了打开这些深度学习模型的黑箱,已经提出了事后实例级解释方法来理解GNN的预测。这些方法旨在发现能够解释训练好的GNN预测行为的子结构。在本文中,我们从分析上表明,对于一大类解释任务,基于图信息瓶颈(GIB)原理的常规方法存在平凡解,这些解与可解释性的概念不一致。相反,我们认为可以使用改进的GIB原理来避免上述平凡解。我们进一步引入了一种具有理论性能保证的新型因子化解释模型。改进的GIB被用于分析所提出的因子化解释器的结构特性。我们在合成数据集和真实世界数据集上进行了大量实验,以验证我们提出的因子化解释器的有效性。

英文摘要:

Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. To open the black-box of these deep learning models, post-hoc instance-level explanation methods have been proposed to understand GNN predictions. These methods seek to discover substructures that explain the prediction behavior of a trained GNN. In this paper, we show analytically that for a large class of explanation tasks, conventional approaches, which are based on the principle of graph information bottleneck (GIB), admit trivial solutions that do not align with the notion of explainability. Instead, we argue that a modified GIB principle may be used to avoid the aforementioned trivial solutions. We further introduce a novel factorized explanation model with theoretical performance guarantees. The modified GIB is used to analyze the structural properties of the proposed factorized explainer. We conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness of our proposed factorized explainer.

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。

↑