Identity-aware Graph Neural Networks
Identity-aware Graph Neural Networks
复制标题
DOI：
10.1609/aaai.v35i12.17283
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Jiaxuan You;Jonathan M. Gomes-Selman;Rex Ying;J. Leskovec
中科院分区：
文献类型：
--
作者：
Jiaxuan You;Jonathan M. Gomes-Selman;Rex Ying;J. Leskovec
消息传递图神经网络(GNN)为关系数据提供了一个强大的建模框架。然而，现有的GNN的表达能力是由1-Weisfeeller-Lehman(1-WL)图同构检验的上限，这意味着GNN不能预测节点聚类系数和最短路径距离，也不能区分不同的d-正则图。在这里，我们开发了一类消息传递GNN，称为身份感知图神经网络(ID-GNN)，比1-WL测试具有更强的表达能力。ID-GNN为现有GNN的局限性提供了一个最小但功能强大的解决方案。ID-GNN通过在消息传递过程中归纳考虑节点的身份，扩展了现有的GNN体系结构。为了嵌入一个给定的节点，ID-GNN首先提取以该节点为中心的EGO网络，然后进行多轮异质消息传递，其中对中心节点应用不同于EGO网络中其他周围节点的参数集。我们进一步提出了一种简化但更快的ID-GNN版本，该版本注入节点身份信息作为增强的节点特征。此外，两个版本的ID-GNN都代表了消息传递GNN的一般扩展，实验表明，将现有GNN转换为ID-GNN，在挑战节点、边和图属性预测任务时，准确率平均提高40%；在节点和图分类基准上，准确率提高3%；在现实世界链接预测任务上，ROC AUC提高15%。此外，ID-GNN表现出比其他特定于任务的图网络更好或相当的性能。
Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are not able to predict node clustering coefficients and shortest path distances, and cannot differentiate between different d-regular graphs. Here we develop a class of message passing GNNs, named Identity-aware Graph Neural Networks (ID-GNNs), with greater expressive power than the 1-WL test. ID-GNN offers a minimal but powerful solution to limitations of existing GNNs. ID-GNN extends existing GNN architectures by inductively considering nodes’ identities during message passing. To embed a given node, ID-GNN first extracts the ego network centered at the node, then conducts rounds of heterogeneous message passing, where different sets of parameters are applied to the center node than to other surrounding nodes in the ego network. We further propose a simplified but faster version of ID-GNN that injects node identity information as augmented node features. Alto- gether, both versions of ID-GNN represent general extensions of message passing GNNs, where experiments show that transforming existing GNNs to ID-GNNs yields on average 40% accuracy improvement on challenging node, edge, and graph property prediction tasks; 3% accuracy improvement on node and graph classification benchmarks; and 15% ROC AUC improvement on real-world link prediction tasks. Additionally, ID-GNNs demonstrate improved or comparable performance over other task-specific graph networks.