Dynamic graph convolutional networks by semi-supervised contrastive learning

The traditional graph convolutional network(GCN) and its variants usually only propagate node informa-tion through the topology given by the dataset. However, the given topology can only represent a certain relationship and ignore some correlative feature information between nodes, which may make the graph convolutional networks unable to fully utilize the data information. To address the above issue, a novel model named Dynamic Graph Convolutional Networks by Semi-Supervised Contrastive Learning (DGSCL) is proposed in this paper. First, a feature graph is dynamically constructed from the input node features to exploit the potential correlative feature information between nodes. Then, to ensure a high-quality feature graph, a semi-supervised contrastive learning method is designed to learn discriminative node embeddings, which can iteratively refine the constructed feature graph with the learned node embed -dings. Finally, we fuse the node embeddings obtained from the given topology and the dynamic feature graph by two co-attention modules to produce more informative embeddings for the classification task. Through a series of experiments, we demonstrate the competitive performance of our model on seven node classification benchmarks.(c) 2023 Elsevier Ltd. All rights reserved.

Automated summary

The traditional graph convolutional network(GCN) and its variants usually only propagate node information through the given topology, ignoring some correlative feature information between nodes. To address this issue, a novel model named Dynamic Graph Convolutional Networks by Semi-Supervised Contrastive Learning (DGSCL) is proposed in this paper. It constructs a dynamic feature graph from the input node features and fuses it with the given topology using co-attention modules for more informative node embeddings.