Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification

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.

[1]  George Karypis,et al.  Multi-threaded modularity based graph clustering using the multilevel paradigm , 2015, J. Parallel Distributed Comput..

[2]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[3]  Heinrich Müller,et al.  SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Dahua Lin,et al.  Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition , 2018, AAAI.

[6]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[7]  Ruslan Salakhutdinov,et al.  Revisiting Semi-Supervised Learning with Graph Embeddings , 2016, ICML.

[8]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[9]  Bruce Hendrickson,et al.  A Multi-Level Algorithm For Partitioning Graphs , 1995, Proceedings of the IEEE/ACM SC95 Conference.

[10]  Xing Xie,et al.  Session-based Recommendation with Graph Neural Networks , 2018, AAAI.

[11]  Ken-ichi Kawarabayashi,et al.  Representation Learning on Graphs with Jumping Knowledge Networks , 2018, ICML.

[12]  Srinivasan Parthasarathy,et al.  MILE: A Multi-Level Framework for Scalable Graph Embedding , 2018, ICWSM.

[13]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[14]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[15]  Vipin Kumar,et al.  A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs , 1998, SIAM J. Sci. Comput..

[16]  Steven Skiena,et al.  HARP: Hierarchical Representation Learning for Networks , 2017, AAAI.

[17]  Haibo Chen,et al.  Visual analysis of large heterogeneous network through interactive centrality based sampling , 2017, 2017 IEEE 14th International Conference on Networking, Sensing and Control (ICNSC).

[18]  Xiao-Ming Wu,et al.  Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning , 2018, AAAI.

[19]  Xiaoyu Zhang,et al.  Dressing as a Whole: Outfit Compatibility Learning Based on Node-wise Graph Neural Networks , 2019, WWW.

[20]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[21]  Jonathan Masci,et al.  Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).