Corruption-free Single-view Self-supervised Learning on Graphs

Tianyi Zhang, Zhenwei DAI, Zhaozhuo Xu, Anshumali Shrivastava

Abstract: Self-supervised learning (SSL) for graphs is an essential problem since graph data are ubiquitous and data labeling is costly. We argue that existing SSL approaches for graphs have two limitations. First, they rely on corruption techniques such as node attribute perturbation and edge dropping to generate graph views for contrastive learning. These unnatural corruption techniques require extensive tuning efforts and provide marginal improvements. Second, the current approaches require the computation of multiple graph views, which is memory and computationally inefficient. These shortcomings of graph SSL call for a corruption-free single-view learning approach, but the strawman approach of using neighboring nodes as positive examples suffers two problems: it ignores the strength of connections between nodes implied by the graph structure on a macro level, and cannot deal with the high noise in real-world graphs. We propose CURSIVE, a corruption-free single-view graph SSL approach that overcomes these problems by leveraging graph diffusion to measure connection strength and denoise. With extensive experiments, we show that CURSIVE achieves up to $4.55\%$ absolute improvement in ROC-AUC on graph SSL tasks over state-of-the-art approaches while being more memory efficient. Moreover, CURSIVE even outperforms supervised training on node classification tasks of ogbn-proteins dataset.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Unsupervised and Self-supervised learning