Barlow Graph Auto-Encoder for Unsupervised Network Embedding

TL;DR

This paper introduces Barlow Graph Auto-Encoder, a novel unsupervised network embedding method inspired by self-supervised learning principles, which improves link prediction, clustering, and node classification performance.

Contribution

It proposes a new architecture that maximizes similarity of neighborhood embeddings while reducing redundancy, extending the Barlow Twins concept to graph data.

Findings

Effective for inductive link prediction

Competitive with state-of-the-art in clustering

Performs well in node classification tasks

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.