Preserving node similarity adversarial learning graph representation with graph neural network

Abstract

Abstract In recent years, graph neural networks (GNNs) have showcased a strong ability to learn graph representations and have been widely used in various practical applications. However, many currently proposed GNN‐based representation learning methods do not retain neighbor‐based node similarity well, and this structural information is crucial in many cases. To address this issue, drawing inspiration from generative adversarial networks (GANs), we propose PNS‐AGNN (i.e., Preserving Node Similarity Adversarial Graph Neural Networks), a novel framework for acquiring graph representations, which can preserve neighbor‐based node similarity of the original graph and efficiently extract the nonlinear structural features of the graph. Specifically, we propose a new positive sample allocation strategy based on a node similarity index, where the generator can generate vector representations that satisfy node similarity through adversarial training. In addition, we also adopt an improved GNN as the discriminator, which utilizes the original graph structure for recursive neighborhood aggregation to maintain the local structure and feature information of nodes, thereby enhancing the graph representation's ability. Finally, we experimentally demonstrate that PNS‐AGNN significantly improves various tasks, including link prediction, node classification, and visualization.

Keywords

• generative adversarial networks
• graph representation learning
• graph neural networks
• node similarity