Research map / Graph learning / GNN architectures
Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks
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 |
|---|---|---|---|
| add hierarchical higher-order (2- and 3-set) GNN layers | 1-GNN · IMDB-BINARY | accuracy: 71.2 -> 74.2 | Helped |
| add hierarchical higher-order GNN layers | 1-GNN · QM9 alpha | MAE: 0.78 -> 0.27 | Helped |
| add hierarchical higher-order GNN layers | 1-GNN · QM9 HOMO | MAE: 0.00321 -> 0.00337 | Hurt |
| train GNN aggregation parameters instead of random (ablation) | 1-2-3-GNN · NCI1 | accuracy: 67.4 -> 76.2 | Helped |
| train GNN aggregation parameters instead of random (ablation) | 1-2-3-GNN · PROTEINS | accuracy: 75.9 -> 75.5 | Hurt |
| add extra layers to 1-GNN to match k-GNN parameter count (ablation) | 1-GNN · all | accuracy/MAE | No clear effect |
| higher-order GNN vs graph kernels | 1-2-3-GNN · NCI1 | accuracy: 86.1 -> 76.2 | Hurt |
Closest papers by meaning
- A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?" (ICLR 2022 · similarity 0.92)
- $\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks (ICLR 2023 · similarity 0.91)
- Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms (ICML 2025 · similarity 0.91)
- Weisfeiler-Leman at the margin: When more expressivity matters (ICML 2024 · similarity 0.91)
- Homomorphism Expressivity of Spectral Invariant Graph Neural Networks (ICLR 2025 · similarity 0.89)
- Schur Nets: exploiting local structure for equivariance in higher order graph neural networks (NeurIPS 2024 · 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.