Robust Graph Data Learning via Latent Graph Convolutional Representation

26 Apr 2019  ·  Bo Jiang, Ziyan Zhang, Bin Luo ·

Graph Convolutional Representation (GCR) has achieved impressive performance for graph data representation. However, existing GCR is generally defined on the input fixed graph which may restrict the representation capacity and also be vulnerable to the structural attacks and noises. To address this issue, we propose a novel Latent Graph Convolutional Representation (LatGCR) for robust graph data representation and learning. Our LatGCR is derived based on reformulating graph convolutional representation from the aspect of graph neighborhood reconstruction. Given an input graph $\textbf{A}$, LatGCR aims to generate a flexible latent graph $\widetilde{\textbf{A}}$ for graph convolutional representation which obviously enhances the representation capacity and also performs robustly w.r.t graph structural attacks and noises. Moreover, LatGCR is implemented in a self-supervised manner and thus provides a basic block for both supervised and unsupervised graph learning tasks. Experiments on several datasets demonstrate the effectiveness and robustness of LatGCR.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification Citeseer GOCN Accuracy 71.8% # 49
Node Classification Cora GOCN Accuracy 84.8% # 29
Node Classification Pubmed GOCN Accuracy 79.7% # 39

Methods