Unsupervised Deep Manifold Attributed Graph Embedding

Abstract

Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space. Existing methods concentrate on learning latent representation via reconstruction tasks, but cannot directly optimize representation and are prone to oversmoothing, thus limiting the applications on downstream tasks. To alleviate these issues, we propose a novel graph embedding framework named Deep Manifold Attributed Graph Embedding (DMAGE). A node-to-node geodesic similarity is proposed to compute the inter-node similarity between the data space and the latent space and then use Bergman divergence as loss function to minimize the difference between them. We then design a new network structure with fewer aggregation to alleviate the oversmoothing problem and incorporate graph structure augmentation to improve the representation's stability. Our proposed DMAGE surpasses state-of-the-art methods by a significant margin on three downstream tasks: unsupervised visualization, node clustering, and link prediction across four popular datasets.

arXiv admin note: text overlap with arXiv:2007.01594 by other authors

References in corpus (10)

• Semi-Supervised Classification with Graph Convolutional Networks
• Distributed Representations of Sentences and Documents
• Finding community structure in networks using the eigenvectors of matrices
• Simplifying Graph Convolutional Networks
• Variational Graph Auto-Encoders
• Community Detection as an Inference Problem
• Structural Deep Embedding for Hyper-Networks
• Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning
• Attributed Graph Clustering via Adaptive Graph Convolution
• CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning