Research map / Graph learning / GNN architectures
WL meet VC
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 |
|---|---|---|---|
| increase feature dimension from 4 to 256 (5-layer simple GNN) (ablation) | simple GNN on graph classification datasets · ENZYMES, MCF-7, MUTAGENICITY, NCI1 | test accuracy | Mixed |
| increase feature dimension from 256 to 1024 (ablation) | simple GNN · ENZYMES | test accuracy: 54.7 -> 54.3 | No clear effect |
| increase number of GNN layers from 0 to 2 (feature dim 64) (ablation) | simple GNN · MUTAGENICITY | test accuracy: 75.7 -> 82.5 | Helped |
| increase number of 1-WL color histograms via more layers (ablation) | simple GNN · MUTAGENICITY | train-test gap | Hurt |
| increase bitlength (simulated via feature dimension 4 to 256) for fitting random labels (ablation) | simple GNN on synthetic random-label data · synthetic dataset, graph order 70 | fit accuracy | Helped |
Closest papers by meaning
- $\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks (ICLR 2023 · similarity 0.93)
- On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry (NeurIPS 2026 · similarity 0.90)
- Weisfeiler-Leman at the margin: When more expressivity matters (ICML 2024 · similarity 0.90)
- Towards Bridging Generalization and Expressivity of Graph Neural Networks (ICLR 2025 · similarity 0.90)
- Homomorphism Expressivity of Spectral Invariant Graph Neural Networks (ICLR 2025 · similarity 0.90)
- Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness (ICLR 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.