A gated graph attention network based on dual graph convolution for node embedding

Ruowang Yu

doi:10.1007/s10489-023-04568-7

2023-03-22

PRE

DOI：10.1007/s10489-023-04568-7

原文链接

原文求助

摘要

En 中文

The research on node classification is based on node embeddings. Node classification accuracy can be improved if the embeddings of different nodes are well discriminated. With the rapid development of deep learning, researchers have proposed many graph neural network models (GNNs), such as GCN and GAT, which generally obtain node embeddings by aggregating neighborhood information. However, such methods only emphasize feature aggregation in neighborhoods and do not consider the class labels of nodes, which leads to the oversmoothing problem and weak differences in inter-class nodes. In this paper, we propose a gated graph attention network based on dual graph convolution for node embedding (GGAN-DGC). To strengthen the embedding difference of inter-class nodes, GGAN-DGC introduces a gated attention mechanism. This mechanism utilizes a supervised gated attention (GA) matrix to separate the GNN aggregation process according to the node class, so as to heterogenize the homogenous graphs. The GA matrix is obtained by the dual graph convolutional network (DGC), which can improve the receptive field of the original graph. In addition, GGAN-DGC adopts triplet loss as the global supervision function of node embedding, which can streng-then the class correlation of node embedding at the global level. Finally, based on the obtained node embedding, nodes can be classified correctly. The experimental results on five datasets confirm that our GGAN-DGC model performs better than other representative methods in node classification, especially for datasets with strong heterophily. In addition, we verify that GGAN-DGC can also perform better than other methods in graph classification experiments.

Keyword:

Graph Neural Network (GNNs)

Class correlation

Gated Attention (GA) matrix

Dual Graph Convolutional network (DGC)