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

Sami Abu-El-Haija, Amol Kapoor, Bryan Perozzi, Joonseok Lee
Proceedings of The 35th Uncertainty in Artificial Intelligence Conference, PMLR 115:841-851, 2020.

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.

Cite this Paper

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.} }
Endnote
%0 Conference Paper %T N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification %A Sami Abu-El-Haija %A Amol Kapoor %A Bryan Perozzi %A Joonseok Lee %B Proceedings of The 35th Uncertainty in Artificial Intelligence Conference %C Proceedings of Machine Learning Research %D 2020 %E Ryan P. Adams %E Vibhav Gogate %F pmlr-v115-abu-el-haija20a %I PMLR %P 841--851 %U https://proceedings.mlr.press/v115/abu-el-haija20a.html %V 115 %X 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.
APA
Abu-El-Haija, S., Kapoor, A., Perozzi, B. & Lee, J.. (2020). N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification. Proceedings of The 35th Uncertainty in Artificial Intelligence Conference, in Proceedings of Machine Learning Research 115:841-851 Available from https://proceedings.mlr.press/v115/abu-el-haija20a.html.

Related Material