Research map / Graph learning / GNN architectures
Provably Powerful Graph 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 matrix multiplication to feature-wise MLP blocks (ablation) | Provably Powerful Graph Networks · NCI1 | generalization error | Helped |
| replace the matrix-product model with only the full linear equivariant basis (ablation) | NCI1 comparison · NCI1 | generalization | Hurt |
| add the full linear equivariant basis to matrix product (ablation) | NCI1 comparison · NCI1 | generalization | No clear effect |
| train separate networks for each QM9 target instead of one shared network (ablation) | Provably Powerful Graph Networks · QM9 | number of targets with lowest error: 5 out of the 12 -> 9 out of the 12 | Helped |
Closest papers by meaning
- $\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks (ICLR 2023 · similarity 0.93)
- A Practical, Progressively-Expressive GNN (NeurIPS 2022 · similarity 0.92)
- Homomorphism Expressivity of Spectral Invariant Graph Neural Networks (ICLR 2025 · similarity 0.90)
- An Empirical Study of Realized GNN Expressiveness (ICML 2024 · similarity 0.90)
- Higher-Order Graphon Neural Networks: Approximation and Cut Distance (ICLR 2025 · similarity 0.90)
- Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness (ICLR 2024 · similarity 0.90)
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.