Research map / Graph learning / Graph self-supervised learning
Unsupervised Adversarially Robust Representation Learning on Graphs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the GRV soft margin (ablation) | Ours · Cora, polluted data | accuracy: 69.4$\pm$0.7 -> 70.7$\pm$0.9 | Helped |
| add the GRV soft margin (ablation) | Ours · Citeseer, polluted data | accuracy: 57.5$\pm$2.0 -> 58.4$\pm$1.4 | Helped |
| add the GRV soft margin (ablation) | Ours · Polblogs, polluted data | accuracy: 79.7$\pm$2.1 -> 82.7$\pm$2.2 | Helped |
| add the GRV soft margin (ablation) | Ours · Cora, polluted data | AUC: 68.1$\pm$0.3 -> 69.2$\pm$0.4 | Helped |
| add the GRV soft margin (ablation) | Ours · Citeseer, polluted data | AUC: 58.2$\pm$1.3 -> 59.8$\pm$1.3 | Helped |
| add the GRV soft margin (ablation) | Ours · Polblogs, polluted data | AUC: 90.3$\pm$0.5 -> 91.8$\pm$0.4 | Helped |
| add the GRV soft margin (ablation) | Ours · Cora, polluted data | NMI: 39.2$\pm$8.8 -> 41.4$\pm$4.7 | Helped |
| add the GRV soft margin (ablation) | Ours · Citeseer, polluted data | NMI: 23.5$\pm$1.9 -> 23.6$\pm$2.8 | Helped |
| add the GRV soft margin (ablation) | Ours · Polblogs, polluted data | NMI: 12.6$\pm$9.6 -> 14.8$\pm$2.7 | Helped |
Closest papers by meaning
- Local-Global Defense against Unsupervised Adversarial Attacks on Graphs (AAAI 2023 · similarity 0.93)
- Mitigating Emergent Robustness Degradation while Scaling Graph Learning (ICLR 2024 · similarity 0.91)
- Value at Adversarial Risk: A Graph Defense Strategy against Cost-Aware Attacks (AAAI 2024 · similarity 0.90)
- Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks (ICLR 2024 · similarity 0.90)
- When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning (AAAI 2025 · similarity 0.89)
- Enhancing Graph Classification Robustness with Singular Pooling (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.