Towards Robust Graph Contrastive Learning

02/25/2021
by   Nikola Jovanović, et al.
0

We study the problem of adversarially robust self-supervised learning on graphs. In the contrastive learning framework, we introduce a new method that increases the adversarial robustness of the learned representations through i) adversarial transformations and ii) transformations that not only remove but also insert edges. We evaluate the learned representations in a preliminary set of experiments, obtaining promising results. We believe this work takes an important step towards incorporating robustness as a viable auxiliary task in graph contrastive learning.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset