Research map / Graph learning / GNN architectures
Natural Graph Networks
Pim de Haan, Taco S Cohen, Max Welling
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 |
|---|---|---|---|
| Use natural graph network features and kernels instead of invariant GCN message passing | IcoMNIST · IcoMNIST, Fixed and Sym | accuracy: 96.17 -> 98.82 | Improved |
| Use GCN² message parameterization for natural local graph message passing | Graph classification benchmarks · NCI109 | accuracy: 82.23$\pm$1.42 -> \bf{83.00 $\pm$ 1.89} | Improved |
| Use natural graph network message parameterization rather than invariant GCN | Graph classification benchmarks · Strongly regular graphs | difference rate: 0 -> 1 | Improved |
Closest papers by meaning
- Schur Nets: exploiting local structure for equivariance in higher order graph neural networks (NeurIPS 2024 · similarity 0.91)
- Building powerful and equivariant graph neural networks with structural message-passing (NeurIPS 2020 · similarity 0.90)
- Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks? (NeurIPS 2024 · similarity 0.87)
- A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening (NeurIPS 2024 · similarity 0.87)
- On the Expressivity and Sample Complexity of Node-Individualized Graph Neural Networks (NeurIPS 2024 · similarity 0.87)
- Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective (ICLR 2025 · similarity 0.87)
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.
