Graph neural networks (GNNs) have achieved state-of-the-art performance in graph representation learning. Message passing neural networks, which learn representations through recursively aggregating information from each node and its neighbors, are among the most commonly-used GNNs. However, a wealth of structural information of individual nodes and full graphs is often ignored in such process, which restricts the expressive power of GNNs. Various graph data augmentation methods that enable the message passing with richer structure knowledge have been introduced as one main way to tackle this issue, but they are often focused on individual structure features and difficult to scale up with more structure features. In this work we propose a novel approach, namely collective structure knowledge-augmented graph neural network (CoS-GNN), in which a new message passing method is introduced to allow GNNs to harness a diverse set of node- and graph-level structure features, together with original node features/attributes, in augmented graphs. In doing so, our approach largely improves the structural knowledge modeling of GNNs in both node and graph levels, resulting in substantially improved graph representations. This is justified by extensive empirical results where CoS-GNN outperforms state-of-the-art models in various graph-level learning tasks, including graph classification, anomaly detection, and out-of-distribution generalization.

翻译：图神经网络（GNN）在图表示学习领域取得了最先进的性能。消息传递神经网络是最常用的GNN之一，它通过递归聚合每个节点及其邻居的信息来学习表示。然而，在此过程中，单个节点和完整图的大量结构信息常被忽略，限制了GNN的表达能力。为应对这一问题，引入了多种图数据扩充方法，通过更丰富的结构知识实现消息传递，但这些方法往往侧重于单个结构特征，难以扩展至更多结构特征。本文提出一种新颖方法，即集体结构知识增强图神经网络（CoS-GNN），该方法引入了一种新的消息传递方式，使GNN能够在增强图中利用多样化的节点级和图级结构特征，同时结合原始节点特征/属性。通过这种方式，我们的方法在节点和图两个层面上显著提升了GNN的结构知识建模能力，从而大幅改进了图表示。大量实验结果表明，CoS-GNN在图分类、异常检测和分布外泛化等多种图级学习任务中均优于现有最先进模型。