提出图结构集成梯度法，精准定位图神经网络的关键结构特征。
Graph-based Integrated Gradients for Explaining Graph Neural Networks
- 将集成梯度扩展到离散图结构，构建图基集成梯度方法。
- 在4个合成数据集上准确识别分类依赖的图结构组件。
- 在3个真实图数据集上优于传统IG，提升节点分类解释效果。
集成梯度（Integrated Gradients, IG）是解释神经网络黑箱行为的常用方法，但其假设数据为连续型，不适用于离散图结构。本文提出图基集成梯度（Graph-based Integrated Gradients, GB-IG），将IG方法拓展至图数据。在四个合成数据集上验证，GB-IG能准确识别用于分类任务的关键图结构成分。在三个典型真实世界图数据集上，GB-IG在节点分类任务中显著优于传统IG，更有效突出重要特征。
原文摘要 · Abstract (English)
Integrated Gradients (IG) is a common explainability technique to address the black-box problem of neural networks. Integrated gradients assumes continuous data. Graphs are discrete structures making IG ill-suited to graphs. In this work, we introduce graph-based integrated gradients (GB-IG); an extension of IG to graphs. We demonstrate on four synthetic datasets that GB-IG accurately identifies crucial structural components of the graph used in classification tasks. We further demonstrate on three prevalent real-world graph datasets that GB-IG outperforms IG in highlighting important features for node classification tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。