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

By Sami Abu-El-Haija, Amol Kapoor, Bryan Perozzi, Joonseok Lee. 2018

295 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Health Information Management

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Health Information Management

Citations in the corpus

Predict then Propagate: Graph Neural Networks meet Personalized PageRank (2018, methodology): “The freedom to choose α allows us to adjust the model for different types of networks, since varying graph types require the consideration of different neighborhood sizes, as shown in Section 6 and described by Grover & Leskovec (2016) and Abu-El-Haija et al. (2018b).”
Simplifying Graph Convolutional Networks (2019, background): “Atwood & Towsley (2016), Abu-El-Haija et al. (2018), and Liao et al. (2019) exploit multi-scale information by raising S to higher order.”
Scaling Graph Neural Networks with Approximate PageRank (2020, background): “[42] and have since emerged as a powerful approach for solving many network mining tasks [1, 2, 9, 17, 22, 32, 42, 44].”
On Filter Size in Graph Convolutional Networks (2018, background): “(7) would be de-ﬁned on the powers of the adjacency matrix, i.e. on random walks [18].”
Multipole Graph Neural Operator for Parametric Partial Differential Equations (2020, background): “Works on multi-resolution graphs with a U-net like structure have also recently began to emerge and seen success in imaging, classiﬁcation, and semi-supervised learning [34, 1, 2, 18, 27].”
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing (2019, background): “Others considered multiple adjacency powers for feature propagation on graphs, including (Abu-El-Haija et al., 2018) and (Atwood & Towsley, 2016) which combine the powers at the end of the network (right before classification layer), and (Lee et al.”
Reliable Data Distillation on Graph Convolutional Network (2020, methodology): “For the other models (LP, Planetoid, LGCN, GPNN, NGCN, DGCN, APPNP and GAT), all the experimental results are drawn from their respective publications.”