Barlow Graph Auto-Encoder for Unsupervised Network Embedding

Abstract

Network embedding has emerged as a promising research field for network analysis. Recently, an approach, named Barlow Twins, has been proposed for self-supervised learning in computer vision by applying the redundancy-reduction principle to the embedding vectors corresponding to two distorted versions of the image samples. Motivated by this, we propose Barlow Graph Auto-Encoder, a simple yet effective architecture for learning network embedding. It aims to maximize the similarity between the embedding vectors of immediate and larger neighborhoods of a node, while minimizing the redundancy between the components of these projections. In addition, we also present the variation counterpart named as Barlow Variational Graph Auto-Encoder. Our approach yields promising results for inductive link prediction and is also on par with state of the art for clustering and downstream node classification, as demonstrated by extensive comparisons with several well-known techniques on three benchmark citation datasets.

References in corpus (9)

• Stochastic blockmodels and community structure in networks
• Variational Graph Auto-Encoders
• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• Contrastive Multi-View Representation Learning on Graphs
• Attributed Graph Clustering: A Deep Attentional Embedding Approach
• Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning
• Stochastic Blockmodels meet Graph Neural Networks
• Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning
• Calibrating and Improving Graph Contrastive Learning