Research map / Graph learning / GNN architectures
Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
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 f3 instead of f1 as the only propagation rule (ablation) | Modular GCN · BA-ER graph classification | test accuracy: 53.5 % -> 76.9 % | Helped |
| Add f3 to f1 (ablation) | Modular GCN · BA-ER graph classification | test accuracy: 53.5 % -> 89.4 % | Helped |
| Add f2 to f1 and f3 (ablation) | Modular GCN · BA-ER graph classification | test accuracy: 89.4 % -> 98.8 % | Helped |
| Use all three propagation rules rather than only f1 (ablation) | Modular GCN · BA-ER graph classification | test accuracy: 53.5 % -> 98.8 % | Helped |
| Increase depth by one layer | Modular GCN · BA-ER and BA-Config graph classification | test accuracy: at least 5% | Helped |
| Increase layer width | Modular GCN · BA-ER and BA-Config graph classification | test accuracy | No clear effect |
Closest papers by meaning
- Graph Neural Networks Exponentially Lose Expressive Power for Node Classification (ICLR 2020 · similarity 0.92)
- How Powerful are Graph Neural Networks? (ICLR 2019 · similarity 0.91)
- Simplifying Graph Convolutional Networks (ICML 2019 · similarity 0.90)
- Why Do Attributes Propagate in Graph Convolutional Neural Networks? (AAAI 2021 · similarity 0.90)
- Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning (AAAI 2018 · similarity 0.90)
- A Manifold Perspective on the Statistical Generalization of Graph Neural Networks (ICML 2025 · similarity 0.89)
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.