Research map / Graph learning / GNN architectures
Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks
Pascal Esser, Leena Chennuru Vankadara, Debarghya Ghoshdastidar
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 |
|---|---|---|---|
| increase alignment between node features and graph (Gamma) in the planted SBM | GNN transductive Rademacher bound · SBM and Cora (noise-simulated) | generalisation error | Hurt |
| increase graph size n | GNN · SBM and Cora | generalisation error | No clear effect |
| increase number of observed labelled nodes m | GNN · SBM and Cora | generalisation error | Improved |
| increase depth K of vanilla GNN | GNN · SBM and Cora | generalisation error | Hurt |
| add residual (GCNII-style initial-residual) connections | GNN · SBM and Cora | generalisation error | Improved |
Closest papers by meaning
- A Manifold Perspective on the Statistical Generalization of Graph Neural Networks (ICML 2025 · similarity 0.91)
- On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry (NeurIPS 2026 · similarity 0.90)
- Generalization Error of Graph Neural Networks in the Mean-field Regime (ICML 2024 · similarity 0.90)
- Towards Bridging Generalization and Expressivity of Graph Neural Networks (ICLR 2025 · similarity 0.89)
- On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.89)
- Graph neural networks and non-commuting operators (NeurIPS 2024 · 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.
