Research map / Graph learning / GNN architectures
ES-GNN: Generalizing Graph Neural Networks Beyond Homophily With Edge Splitting
Jingwei Guo, Kaizhu Huang, Rui Zhang, Xinping Yi
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 |
|---|---|---|---|
| add the edge-splitting ES-layer (ablation) | ES-GNN · Synthetic graphs (avg) | accuracy (%): 75.4 -> 85.3 | Improved |
| add the edge-splitting ES-layer (ablation) | ES-GNN · Synthetic graphs (homophily 0.3) | accuracy (%): 53.3 -> 62.1 | Improved |
| add the edge-splitting ES-layer (ablation) | ES-GNN · Synthetic graphs (homophily 0.1) | accuracy (%): 84.6 -> 90.0 | Improved |
| add the edge-splitting ES-layer (ablation) | ES-GNN · Synthetic graphs (homophily 0.9) | accuracy (%): 96.7 -> 100.0 | Improved |
| use ES-GNN instead of ACM-GCN on Squirrel | ACM-GCN · Squirrel | accuracy (%): 67.0 -> 62.4 | Hurt |
| use ES-GNN instead of GloGNN++ | GloGNN++ · Texas | accuracy (%): 81.4 -> 82.3 | Improved |
| use ES-GNN instead of GCN | GCN · Wisconsin | accuracy (%): 59.5 -> 85.3 | Improved |
| use ES-GNN instead of GCN | GCN · Cora | accuracy (%): 79.7 -> 83.0 | Improved |
| use ES-GNN under injected fake edges | GCN/GAT · Perturbed homophilic graphs | accuracy (%) | Improved |
| use ES-GNN on Cora under injected fake edges | baselines · Perturbed Cora | accuracy (%) | No clear effect |
Closest papers by meaning
- Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective (NeurIPS 2025 · similarity 0.92)
- Integrating Co-Training with Edge Discrimination to Enhance Graph Neural Networks Under Heterophily (AAAI 2025 · similarity 0.91)
- Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization (NeurIPS 2025 · similarity 0.90)
- Improving Graph Neural Networks by Learning Continuous Edge Directions (ICLR 2025 · similarity 0.90)
- A Manifold Perspective on the Statistical Generalization of Graph Neural Networks (ICML 2025 · similarity 0.90)
- Towards Bridging Generalization and Expressivity of Graph Neural Networks (ICLR 2025 · 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.
