English

Higher-order Graph Convolutional Networks

Social and Information Networks 2018-09-21 v1 Machine Learning

Abstract

Following the success of deep convolutional networks in various vision and speech related tasks, researchers have started investigating generalizations of the well-known technique for graph-structured data. A recently-proposed method called Graph Convolutional Networks has been able to achieve state-of-the-art results in the task of node classification. However, since the proposed method relies on localized first-order approximations of spectral graph convolutions, it is unable to capture higher-order interactions between nodes in the graph. In this work, we propose a motif-based graph attention model, called Motif Convolutional Networks (MCNs), which generalizes past approaches by using weighted multi-hop motif adjacency matrices to capture higher-order neighborhoods. A novel attention mechanism is used to allow each individual node to select the most relevant neighborhood to apply its filter. Experiments show that our proposed method is able to achieve state-of-the-art results on the semi-supervised node classification task.

Keywords

Cite

@article{arxiv.1809.07697,
  title  = {Higher-order Graph Convolutional Networks},
  author = {John Boaz Lee and Ryan A. Rossi and Xiangnan Kong and Sungchul Kim and Eunyee Koh and Anup Rao},
  journal= {arXiv preprint arXiv:1809.07697},
  year   = {2018}
}