Research map / Graph learning / GNN architectures
From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive 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 node ID labels to l nodes (l>=2) to MPNN (ID-MPNN) | MPNN · EXP and SR25 graph isomorphism | accuracy: GIN 50 -> 100 on EXP; 6.67 -> 100 on SR25 | Helped |
| Add node ID labels (l>=2) to PPGN (ID-PPGN) | PPGN · SR25 | accuracy: 6.67 -> 100 | Helped |
| Use ID-MPNN with l=4 instead of standard baselines on ZINC12k | MPNN · ZINC12k | test MAE: 4-IDMPNN 0.083 vs GPS 0.070 (best) | Mixed |
| Use 4-IDMPNN on ogbg-molhiv | MPNN · ogbg-molhiv | test AUC: 79.31 vs CIN 80.94 | Mixed |
| Use 4-IDMPNN on QM9 | MPNN · QM9 (12 targets) | MAE: superior on 7 of 12 targets | Helped |
| Restrict ID-MPNN (l = target substructure size) to labeled tuples for substructure counting | MPNN · Random regular graph substructure counting (triangle) | test MAE: 5.86E-46 vs GIN-AK+ 1.23E-2 | Helped |
Closest papers by meaning
- A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening (NeurIPS 2024 · similarity 0.91)
- Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness (ICLR 2024 · similarity 0.91)
- Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products (ICML 2024 · similarity 0.91)
- Homomorphism Expressivity of Spectral Invariant Graph Neural Networks (ICLR 2025 · similarity 0.90)
- Towards Bridging Generalization and Expressivity of Graph Neural Networks (ICLR 2025 · similarity 0.90)
- On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry (NeurIPS 2026 · 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.