Research map / Adversarial robustness and security / Attacks on text and graphs
Improving the Robustness of Wasserstein Embedding by Adversarial PAC-Bayesian Learning
Daizong Ding, Mi Zhang, Xudong Pan, Min Yang, Xiangnan He
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| RAWEN instead of best baseline DVNE | node embedding · Google link prediction | precision: 5% | Improved |
| adversarial PAC-Bayesian training (RAWEN) under 18% edge noise | node embedding · Wiki-Vote link prediction, noise level 6 | AUC: 2% decrease vs 10% decrease | Improved |
| distribution-based embedding (DVNE) instead of vector-based embeddings | node embedding baselines · link prediction | precision and recall | Improved |
| add adversarial learning (GANE) to vector-based embedding | vector-based embedding · link prediction | precision and recall | Improved |
| use Gaussian instead of Dirichlet or truncated Gaussian embedding distribution (ablation) | RAWEN · link prediction | precision and recall | Improved |
| choice of embedding distribution (Gaussian, Dirichlet, truncated Gaussian) (ablation) | RAWEN · node classification (Email, Wiki) | Macro/Micro-F1 | No clear effect |
| use Dirichlet distribution for embeddings (ablation) | RAWEN · t-SNE visualization | clustering structure (qualitative) | Improved |
Closest papers by meaning
- Adversarial Network Embedding (AAAI 2018 · similarity 0.88)
- Wasserstein Embedding for Graph Learning (ICLR 2021 · similarity 0.88)
- Asymptotics of $\ell_2$ Regularized Network Embeddings (NeurIPS 2022 · similarity 0.87)
- Unsupervised Adversarially Robust Representation Learning on Graphs (AAAI 2022 · similarity 0.87)
- WatE: A Wasserstein t-distributed Embedding Method for Information-enriched Graph Visualization (AAAI 2025 · similarity 0.85)
- SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning (ICML 2025 · similarity 0.85)
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.
