Research map / Graph learning / GNN architectures
On the Ability of Graph Neural Networks to Model Interactions Between Vertices
Noam Razin, Tom Verbin, Nadav Cohen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Use a high-walk-index rather than low-walk-index essential partition | GCN · Fashion-MNIST graph prediction | train accuracy: 70.4 -> 81.4 | Improved |
| Use a high-walk-index rather than low-walk-index essential partition | GCN · Fashion-MNIST graph prediction | test accuracy: 52.7 -> 66.2 | Improved |
| Use a high-walk-index rather than low-walk-index essential partition | GAT · Fashion-MNIST graph prediction | train accuracy: 82.8 -> 88.5 | Improved |
| Use a high-walk-index rather than low-walk-index essential partition | GAT · Fashion-MNIST graph prediction | test accuracy: 69.6 -> 72.1 | Improved |
| Use a high-walk-index rather than low-walk-index essential partition | GIN · Fashion-MNIST graph prediction | train accuracy: 83.2 -> 94.2 | Improved |
| Use a high-walk-index rather than low-walk-index essential partition | GIN · Fashion-MNIST graph prediction | test accuracy: 53.7 -> 64.8 | Improved |
| Sparsify edges using WIS rather than random removal, spectral sparsification, or adapted UGS | GCN · Cora, DBLP, OGBN-ArXiv | test accuracy | Improved |
| Use 1-WIS instead of depth-compatible 2-WIS (ablation) | GCN · Cora | test accuracy | No clear effect |
Closest papers by meaning
- Expressiveness and Approximation Properties of Graph Neural Networks (ICLR 2022 · similarity 0.89)
- Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality (ICML 2025 · similarity 0.88)
- Explaining Graph Neural Networks via Structure-aware Interaction Index (ICML 2024 · similarity 0.88)
- Towards Bridging Generalization and Expressivity of Graph Neural Networks (ICLR 2025 · similarity 0.88)
- Covered Forest: Fine-grained generalization analysis of graph neural networks (ICML 2025 · similarity 0.88)
- Bridging Theory and Practice in Link Representation with Graph Neural Networks (NeurIPS 2025 · similarity 0.88)
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.
