Research map / Graph learning / GNN architectures
A Theoretical Comparison of Graph Neural Network Extensions
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 markings (M_k) instead of node removal as symmetry-breaking approach (GNNs with markings) | GNN with markings vs node removal · theoretical expressiveness (graph pairs) | distinguishability of graph pairs | Helped |
| Use marked-node-specific aggregation and update functions (markings) so the GNN is injective over marked/unmarked neighbors | GNNs with markings · theoretical expressiveness | distinguishability under k-markings | Helped |
| Add two markings (M_2) relative to 2-WL | GNN with markings · Rook's 4x4 vs Shrikhande graphs | distinguishability | Helped |
| Add 4-clique counting features (S_4) relative to 2-WL | S_k GNN · graph pairs counting 4-cliques | distinguishability | Helped |
| Increase k for N_k (ego-network radius) in comparisons with S_k | N_k vs S_k · theoretical | distinguishability | Mixed |
Closest papers by meaning
- $\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks (ICLR 2023 · similarity 0.92)
- A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests (ICML 2023 · similarity 0.92)
- Rethinking the Expressive Power of GNNs via Graph Biconnectivity (ICLR 2023 · similarity 0.92)
- Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness (ICLR 2024 · similarity 0.92)
- Towards Bridging Generalization and Expressivity of Graph Neural Networks (ICLR 2025 · similarity 0.91)
- An Empirical Study of Realized GNN Expressiveness (ICML 2024 · similarity 0.91)
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.