Research map / Graph learning / GNN architectures
USER: Unsupervised Structural Entropy-Based Robust Graph Neural Network
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 |
|---|---|---|---|
| use USER instead of the strongest listed baseline | GAE-supported graph representation learning · Cora, 50% random-noise clustering | NMI: 43.22±0.69 -> 49.33±1.95 | Helped |
| use USER instead of the strongest listed baseline | GAE-supported graph representation learning · Citeseer, 50% random-noise clustering | NMI: 29.58±0.94 -> 34.5±2.1 | Helped |
| use USER instead of the strongest listed baseline | GAE-supported graph representation learning · Wiki, 50% random-noise clustering | NMI: 46.83±0.58 -> 48.68±1.78 | Helped |
| use USER instead of the strongest listed baseline | GAE-supported graph representation learning · Citeseer and Wiki, 50% random-noise link prediction | AUC: 91.85±0.87 -> 94.54±0.24; 76.79±2.16 -> 86.87±0.4 | Helped |
| use USER instead of the strongest listed baseline | GAE-supported graph representation learning · Citeseer and Wiki, 50% random-noise link prediction | AP: 92.73±0.71 -> 95.05±0.19; 80.29±1.83 -> 88.28±0.38 | Helped |
| add NPSI (ablation) | USER · Cora, Citeseer, and Wiki, 10% random-noise clustering | NMI: 14.82 -> 54.38; 28.95 -> 37.04; 48.44 -> 48.97 | Helped |
| add DBI (ablation) | USER · Cora, 10% random-noise clustering | NMI: 52.54 -> 54.38 | Helped |
| add DBI (ablation) | USER · Citeseer and Wiki, 10% random-noise clustering | NMI: 12.82 -> 37.04; 37.28 -> 48.97 | Helped |
| learn A' rather than fixing it to the original input graph (ablation) | USER · Cora, Citeseer, and Wiki, 10% random-noise clustering | NMI: 40.11 -> 54.38; 30.94 -> 37.04; 39.77 -> 48.97 | Helped |
Closest papers by meaning
- Structural Entropy Based Graph Structure Learning for Node Classification (AAAI 2024 · similarity 0.89)
- Rethinking Independent Cross-Entropy Loss For Graph-Structured Data (ICML 2024 · similarity 0.87)
- Structural Entropy Guided Unsupervised Graph Out-Of-Distribution Detection (AAAI 2025 · similarity 0.87)
- On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.86)
- Learning Latent Graph Structures and their Uncertainty (ICML 2025 · similarity 0.86)
- LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering (ICML 2024 · similarity 0.86)
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.