N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification

Abstract

Graph Convolutional Networks (GCNs) have shown significant improvements in semi-supervised learning on graph-structured data. Concurrently, unsupervised learning of graph embeddings has benefited from the information contained in random walks. In this paper, we propose a model: Network of GCNs (N-GCN), which marries these two lines of work. At its core, N-GCN trains multiple instances of GCNs over node pairs discovered at different distances in random walks, and learns a combination of the instance outputs which optimizes the classification objective. Our experiments show that our proposed N-GCN model improves state-of-the-art baselines on all of the challenging node classification tasks we consider: Cora, Citeseer, Pubmed, and PPI. In addition, our proposed method has other desirable properties, including generalization to recently proposed semi-supervised learning methods such as GraphSAGE, allowing us to propose N-SAGE, and resilience to adversarial input perturbations.

References in corpus (3)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Cited by in corpus (13)

• Scaling Graph Neural Networks with Approximate PageRank
• Multipole Graph Neural Operator for Parametric Partial Differential Equations
• Directed Graph Convolutional Network
• SPAGAN: Shortest Path Graph Attention Network
• SCE: Scalable Network Embedding from Sparsest Cut
• Semi-Supervised Node Classification by Graph Convolutional Networks and Extracted Side Information
• L${}^2$-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks
• The Impact of Global Structural Information in Graph Neural Networks Applications
• Multi-Channel Graph Convolutional Networks
• Topological based classification using graph convolutional networks
• Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
• Multiscale Laplacian Learning
• An Uncoupled Training Architecture for Large Graph Learning