Barlow Graph Auto-Encoder for Unsupervised Network Embedding
This work addresses network analysis for researchers, offering an incremental improvement by adapting a computer vision method to graph data.
The paper tackled unsupervised network embedding by proposing Barlow Graph Auto-Encoder, which maximizes similarity between node neighborhood embeddings while minimizing redundancy, achieving competitive results for inductive link prediction, clustering, and node classification on citation datasets.
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.