Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification
This addresses the need for better global information capture in semi-supervised node classification, particularly with few labeled samples, but is incremental as it builds on existing GCN frameworks.
The paper tackles the problem of limited receptive fields in shallow graph convolutional networks for node classification by proposing a deep hierarchical model that aggregates nodes to hyper-nodes and refines the graph, achieving up to 5.9% accuracy improvement over state-of-the-art methods.
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.