SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning

Junran Wu, Xueyuan Chen, Bowen Shi, Shangzhe Li, Ke Xu
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37293-37312, 2023.

Abstract

In contrastive learning, the choice of "view" controls the information that the representation captures and influences the performance of the model. However, leading graph contrastive learning methods generally produce views via random corruption or learning, which could lead to the loss of essential information and alteration of semantic information. An anchor view that maintains the essential information of input graphs for contrastive learning has been hardly investigated. In this paper, based on the theory of graph information bottleneck, we deduce the definition of this anchor view; put differently, the anchor view with essential information of input graph is supposed to have the minimal structural uncertainty. Furthermore, guided by structural entropy, we implement the anchor view, termed SEGA, for graph contrastive learning. We extensively validate the proposed anchor view on various benchmarks regarding graph classification under unsupervised, semi-supervised, and transfer learning and achieve significant performance boosts compared to the state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-wu23a, title = {{SEGA}: Structural Entropy Guided Anchor View for Graph Contrastive Learning}, author = {Wu, Junran and Chen, Xueyuan and Shi, Bowen and Li, Shangzhe and Xu, Ke}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {37293--37312}, 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/wu23a/wu23a.pdf}, url = {https://proceedings.mlr.press/v202/wu23a.html}, abstract = {In contrastive learning, the choice of "view" controls the information that the representation captures and influences the performance of the model. However, leading graph contrastive learning methods generally produce views via random corruption or learning, which could lead to the loss of essential information and alteration of semantic information. An anchor view that maintains the essential information of input graphs for contrastive learning has been hardly investigated. In this paper, based on the theory of graph information bottleneck, we deduce the definition of this anchor view; put differently, the anchor view with essential information of input graph is supposed to have the minimal structural uncertainty. Furthermore, guided by structural entropy, we implement the anchor view, termed SEGA, for graph contrastive learning. We extensively validate the proposed anchor view on various benchmarks regarding graph classification under unsupervised, semi-supervised, and transfer learning and achieve significant performance boosts compared to the state-of-the-art methods.} }
Endnote
%0 Conference Paper %T SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning %A Junran Wu %A Xueyuan Chen %A Bowen Shi %A Shangzhe Li %A Ke Xu %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-wu23a %I PMLR %P 37293--37312 %U https://proceedings.mlr.press/v202/wu23a.html %V 202 %X In contrastive learning, the choice of "view" controls the information that the representation captures and influences the performance of the model. However, leading graph contrastive learning methods generally produce views via random corruption or learning, which could lead to the loss of essential information and alteration of semantic information. An anchor view that maintains the essential information of input graphs for contrastive learning has been hardly investigated. In this paper, based on the theory of graph information bottleneck, we deduce the definition of this anchor view; put differently, the anchor view with essential information of input graph is supposed to have the minimal structural uncertainty. Furthermore, guided by structural entropy, we implement the anchor view, termed SEGA, for graph contrastive learning. We extensively validate the proposed anchor view on various benchmarks regarding graph classification under unsupervised, semi-supervised, and transfer learning and achieve significant performance boosts compared to the state-of-the-art methods.
APA
Wu, J., Chen, X., Shi, B., Li, S. & Xu, K.. (2023). SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:37293-37312 Available from https://proceedings.mlr.press/v202/wu23a.html.

Related Material