UAI 2019poster356 citations

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

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

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.

BibTeX
@InProceedings{pmlr-v115-abu-el-haija20a,
  title = 	 {N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification},
  author =       {Abu-El-Haija, Sami and Kapoor, Amol and Perozzi, Bryan and Lee, Joonseok},
  booktitle = 	 {Proceedings of The 35th Uncertainty in Artificial Intelligence Conference},
  pages = 	 {841--851},
  year = 	 {2020},
  editor = 	 {Adams, Ryan P. and Gogate, Vibhav},
  volume = 	 {115},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {22--25 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v115/abu-el-haija20a/abu-el-haija20a.pdf},
  url = 	 {https://proceedings.mlr.press/v115/abu-el-haija20a.html},
  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.}
}
N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification · UAI 2019