Harnessing Collective Structure Knowledge in Data Augmentation for Graph Neural Networks
This addresses the limitation of GNNs in modeling structural knowledge, which is crucial for applications in graph-level learning tasks such as classification and anomaly detection, representing an incremental improvement over existing augmentation methods.
The paper tackled the problem of graph neural networks (GNNs) ignoring structural information by proposing CoS-GNN, a method that incorporates diverse node- and graph-level structure features into message passing, resulting in substantially improved graph representations and outperforming state-of-the-art models in tasks like graph classification and anomaly detection.
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.