Robust Graph Data Learning via Latent Graph Convolutional Representation
This addresses the problem of vulnerability to structural attacks and noises in graph data learning for researchers and practitioners in graph neural networks, though it appears incremental as it builds on existing GCR methods.
The paper tackled the limitation of Graph Convolutional Representation (GCR) being defined on fixed input graphs, which restricts representation capacity and is vulnerable to structural attacks and noises, by proposing Latent Graph Convolutional Representation (LatGCR) that generates a flexible latent graph for robust representation, with experiments showing effectiveness and robustness on several datasets.
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.