Barlow Graph Auto-Encoder for Unsupervised Network Embedding

Rayyan Ahmad Khan, Martin Kleinsteuber
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:306-322, 2023.

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 variational counterpart named Barlow Variational Graph Auto-Encoder. We demonstrate the effectiveness of our approach in learning multiple graph-related tasks, i.e., link prediction, clustering, and downstream node classification, by providing extensive comparisons with several well-known techniques on eight benchmark datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v206-khan23a, title = {Barlow Graph Auto-Encoder for Unsupervised Network Embedding}, author = {Khan, Rayyan Ahmad and Kleinsteuber, Martin}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {306--322}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/khan23a/khan23a.pdf}, url = {https://proceedings.mlr.press/v206/khan23a.html}, 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 variational counterpart named Barlow Variational Graph Auto-Encoder. We demonstrate the effectiveness of our approach in learning multiple graph-related tasks, i.e., link prediction, clustering, and downstream node classification, by providing extensive comparisons with several well-known techniques on eight benchmark datasets.} }
Endnote
%0 Conference Paper %T Barlow Graph Auto-Encoder for Unsupervised Network Embedding %A Rayyan Ahmad Khan %A Martin Kleinsteuber %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-khan23a %I PMLR %P 306--322 %U https://proceedings.mlr.press/v206/khan23a.html %V 206 %X 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 variational counterpart named Barlow Variational Graph Auto-Encoder. We demonstrate the effectiveness of our approach in learning multiple graph-related tasks, i.e., link prediction, clustering, and downstream node classification, by providing extensive comparisons with several well-known techniques on eight benchmark datasets.
APA
Khan, R.A. & Kleinsteuber, M.. (2023). Barlow Graph Auto-Encoder for Unsupervised Network Embedding. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:306-322 Available from https://proceedings.mlr.press/v206/khan23a.html.

Related Material