Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification

Abstract

Graph convolutional networks (GCNs) have been successfully applied in node classification tasks of network mining. However, most of these models based on neighborhood aggregation are usually shallow and lack the "graph pooling" mechanism, which prevents the model from obtaining adequate global information. In order to increase the receptive field, we propose a novel deep Hierarchical Graph Convolutional Network (H-GCN) for semi-supervised node classification. H-GCN first repeatedly aggregates structurally similar nodes to hyper-nodes and then refines the coarsened graph to the original to restore the representation for each node. Instead of merely aggregating one- or two-hop neighborhood information, the proposed coarsening procedure enlarges the receptive field for each node, hence more global information can be captured. The proposed H-GCN model shows strong empirical performance on various public benchmark graph datasets, outperforming state-of-the-art methods and acquiring up to 5.9% performance improvement in terms of accuracy. In addition, when only a few labeled samples are provided, our model gains substantial improvements.

8 pages, 3 figures, 3 tables, accepted by International Joint Conference on Artificial Intelligence (IJCAI-19)

Cited by in corpus (6)

• Graph Contrastive Learning with Adaptive Augmentation
• Mining Latent Structures for Multimedia Recommendation
• GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction
• Graph Communal Contrastive Learning
• CenGCN: Centralized Convolutional Networks with Vertex Imbalance for Scale-Free Graphs
• Semi-supervised Network Embedding with Differentiable Deep Quantisation