Variational Graph Normalized Auto-Encoders

Abstract

Link prediction is one of the key problems for graph-structured data. With the advancement of graph neural networks, graph autoencoders (GAEs) and variational graph autoencoders (VGAEs) have been proposed to learn graph embeddings in an unsupervised way. It has been shown that these methods are effective for link prediction tasks. However, they do not work well in link predictions when a node whose degree is zero (i.g., isolated node) is involved. We have found that GAEs/VGAEs make embeddings of isolated nodes close to zero regardless of their content features. In this paper, we propose a novel Variational Graph Normalized AutoEncoder (VGNAE) that utilize L2-normalization to derive better embeddings for isolated nodes. We show that our VGNAEs outperform the existing state-of-the-art models for link prediction tasks. The code is available at https://github.com/SeongJinAhn/VGNAE.

References in corpus (9)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Semi-Supervised Classification with Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• Variational Graph Auto-Encoders
• DeeperGCN: All You Need to Train Deeper GCNs
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning
• Deep Metric Learning with Spherical Embedding
• Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning