Adversarial Robustness of Graph Contrastive Learning vs Traditional Graph Neural Networks

This report synthesises findings from 15 peer-reviewed papers addressing the following research question: How does the adversarial robustness of graph contrastive learning models compare to traditional graph neural networks (GNNs) when evaluated on benchmark datasets like OGB, Cora, or Citeseer under. Deep models trained in supervised mode have achieved remarkable success on a variety of tasks. When labeled samples are limited, self-supervised learning (SSL) is emerging as a new paradigm for making use of large amounts of unlabeled samples. 8 claims were extracted from source literature; 8 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the adversarial robustness of graph contrastive learning models compare to traditional graph neural networks (GNNs) when evaluated on benchmark datasets like OGB, Cora, or Citeseer under targeted node-level perturbations?

Autonomous literature synthesis. Automated review score: 9.0/10. Full text and citation available at Assignee Research.