Universal Graph Contrastive Learning with a Novel Laplacian Perturbation

Taewook Ko, Yoonhyuk Choi, Chong-Kwon Kim
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, PMLR 216:1098-1108, 2023.

Abstract

Graph Contrastive Learning (GCL) is an effective method for discovering meaningful patterns in graph data. By evaluating diverse augmentations of the graph, GCL learns discriminative representations and provides a flexible and scalable mechanism for various graph mining tasks. This paper proposes a novel contrastive learning framework by introducing Laplacian perturbation. The proposed framework offers a distinct advantage by employing an indirect perturbation method, which provides a more stable approach while maintaining the perturbation effects. Moreover, it exhibits a wide range of applicability by not being restricted to specific graph types. We demonstrate that a spectral graph convolution based on the Laplacian successfully extracts representations from diverse graph types. Our extensive experiments on a variety of real-world datasets, covering multiple graph types, show that the proposed model outperforms state-of-the-art baselines in both node classification and link sign prediction tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v216-ko23a, title = {Universal Graph Contrastive Learning with a Novel {L}aplacian Perturbation}, author = {Ko, Taewook and Choi, Yoonhyuk and Kim, Chong-Kwon}, booktitle = {Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence}, pages = {1098--1108}, year = {2023}, editor = {Evans, Robin J. and Shpitser, Ilya}, volume = {216}, series = {Proceedings of Machine Learning Research}, month = {31 Jul--04 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v216/ko23a/ko23a.pdf}, url = {https://proceedings.mlr.press/v216/ko23a.html}, abstract = {Graph Contrastive Learning (GCL) is an effective method for discovering meaningful patterns in graph data. By evaluating diverse augmentations of the graph, GCL learns discriminative representations and provides a flexible and scalable mechanism for various graph mining tasks. This paper proposes a novel contrastive learning framework by introducing Laplacian perturbation. The proposed framework offers a distinct advantage by employing an indirect perturbation method, which provides a more stable approach while maintaining the perturbation effects. Moreover, it exhibits a wide range of applicability by not being restricted to specific graph types. We demonstrate that a spectral graph convolution based on the Laplacian successfully extracts representations from diverse graph types. Our extensive experiments on a variety of real-world datasets, covering multiple graph types, show that the proposed model outperforms state-of-the-art baselines in both node classification and link sign prediction tasks.} }
Endnote
%0 Conference Paper %T Universal Graph Contrastive Learning with a Novel Laplacian Perturbation %A Taewook Ko %A Yoonhyuk Choi %A Chong-Kwon Kim %B Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2023 %E Robin J. Evans %E Ilya Shpitser %F pmlr-v216-ko23a %I PMLR %P 1098--1108 %U https://proceedings.mlr.press/v216/ko23a.html %V 216 %X Graph Contrastive Learning (GCL) is an effective method for discovering meaningful patterns in graph data. By evaluating diverse augmentations of the graph, GCL learns discriminative representations and provides a flexible and scalable mechanism for various graph mining tasks. This paper proposes a novel contrastive learning framework by introducing Laplacian perturbation. The proposed framework offers a distinct advantage by employing an indirect perturbation method, which provides a more stable approach while maintaining the perturbation effects. Moreover, it exhibits a wide range of applicability by not being restricted to specific graph types. We demonstrate that a spectral graph convolution based on the Laplacian successfully extracts representations from diverse graph types. Our extensive experiments on a variety of real-world datasets, covering multiple graph types, show that the proposed model outperforms state-of-the-art baselines in both node classification and link sign prediction tasks.
APA
Ko, T., Choi, Y. & Kim, C.. (2023). Universal Graph Contrastive Learning with a Novel Laplacian Perturbation. Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 216:1098-1108 Available from https://proceedings.mlr.press/v216/ko23a.html.

Related Material