Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Augmentation-Free Self-Supervised Learning on Graphs

About

Inspired by the recent success of self-supervised methods applied on images, self-supervised learning on graph structured data has seen rapid growth especially centered on augmentation-based contrastive methods. However, we argue that without carefully designed augmentation techniques, augmentations on graphs may behave arbitrarily in that the underlying semantics of graphs can drastically change. As a consequence, the performance of existing augmentation-based methods is highly dependent on the choice of augmentation scheme, i.e., hyperparameters associated with augmentations. In this paper, we propose a novel augmentation-free self-supervised learning framework for graphs, named AFGRL. Specifically, we generate an alternative view of a graph by discovering nodes that share the local structural information and the global semantics with the graph. Extensive experiments towards various node-level tasks, i.e., node classification, clustering, and similarity search on various real-world datasets demonstrate the superiority of AFGRL. The source code for AFGRL is available at https://github.com/Namkyeong/AFGRL.

Namkyeong Lee, Junseok Lee, Chanyoung Park• 2021

Related benchmarks

TaskDatasetResultRank
Molecular property predictionMoleculeNet BBBP (scaffold)
ROC AUC70.8
117
Molecular property predictionMoleculeNet SIDER (scaffold)
ROC-AUC0.602
97
Molecular property predictionMoleculeNet BACE (scaffold)
ROC-AUC79.3
87
Molecular property predictionMoleculeNet MUV (scaffold)
ROC-AUC0.777
68
Molecular property predictionTOXCAST (scaffold)
ROC-AUC63.1
52
Toxicity PredictionTox21 (scaffold)
AUC0.749
46
Molecular Property ClassificationClinTox (scaffold)
ROC-AUC0.791
42
Molecular Property ClassificationHIV (scaffold)
ROC AUC0.76
25
BP ClassificationBreast Cancer GRN
Subset Accuracy24
11
Hazard PredictionBreast Cancer GRN
C-Index0.616
11
Showing 10 of 10 rows

Other info

Follow for update