2019/04/26 by Bo Jiang, Jiang, Bo, Ziyan Zhang +3
Computer Science · Decision Sciences · #Advanced Graph Neural Networks #Computer Vision and Pattern Recognition (cs.CV) #Data Quality and Management #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1904.11883
openalex publication_date 2019/04/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 A, LatGCR aims to generate a flexible latent graph \widetildeA 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.