Randomized Schur Complement Views for Graph Contrastive Learning

Vignesh Kothapalli
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17580-17614, 2023.

Abstract

We introduce a randomized topological augmentor based on Schur complements for Graph Contrastive Learning (GCL). Given a graph laplacian matrix, the technique generates unbiased approximations of its Schur complements and treats the corresponding graphs as augmented views. We discuss the benefits of our approach, provide theoretical justifications and present connections with graph diffusion. Unlike previous efforts, we study the empirical effectiveness of the augmentor in a controlled fashion by varying the design choices for subsequent GCL phases, such as encoding and contrasting. Extensive experiments on node and graph classification benchmarks demonstrate that our technique consistently outperforms pre-defined and adaptive augmentation approaches to achieve state-of-the-art results.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-kothapalli23a, title = {Randomized Schur Complement Views for Graph Contrastive Learning}, author = {Kothapalli, Vignesh}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {17580--17614}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/kothapalli23a/kothapalli23a.pdf}, url = {https://proceedings.mlr.press/v202/kothapalli23a.html}, abstract = {We introduce a randomized topological augmentor based on Schur complements for Graph Contrastive Learning (GCL). Given a graph laplacian matrix, the technique generates unbiased approximations of its Schur complements and treats the corresponding graphs as augmented views. We discuss the benefits of our approach, provide theoretical justifications and present connections with graph diffusion. Unlike previous efforts, we study the empirical effectiveness of the augmentor in a controlled fashion by varying the design choices for subsequent GCL phases, such as encoding and contrasting. Extensive experiments on node and graph classification benchmarks demonstrate that our technique consistently outperforms pre-defined and adaptive augmentation approaches to achieve state-of-the-art results.} }
Endnote
%0 Conference Paper %T Randomized Schur Complement Views for Graph Contrastive Learning %A Vignesh Kothapalli %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-kothapalli23a %I PMLR %P 17580--17614 %U https://proceedings.mlr.press/v202/kothapalli23a.html %V 202 %X We introduce a randomized topological augmentor based on Schur complements for Graph Contrastive Learning (GCL). Given a graph laplacian matrix, the technique generates unbiased approximations of its Schur complements and treats the corresponding graphs as augmented views. We discuss the benefits of our approach, provide theoretical justifications and present connections with graph diffusion. Unlike previous efforts, we study the empirical effectiveness of the augmentor in a controlled fashion by varying the design choices for subsequent GCL phases, such as encoding and contrasting. Extensive experiments on node and graph classification benchmarks demonstrate that our technique consistently outperforms pre-defined and adaptive augmentation approaches to achieve state-of-the-art results.
APA
Kothapalli, V.. (2023). Randomized Schur Complement Views for Graph Contrastive Learning. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:17580-17614 Available from https://proceedings.mlr.press/v202/kothapalli23a.html.

Related Material