Research map / Graph learning / GNN architectures
Are we measuring oversmoothing in graph neural networks correctly?
Kaicheng Zhang, Piero Deidda, Desmond Higham, Francesco Tudisco
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 |
|---|---|---|---|
| measure oversmoothing with effective rank instead of Dirichlet energy | GCN/GAT oversmoothing metric · 7 node classification datasets, depth 2-24 | avg Pearson correlation with accuracy: Erank 0.9103 vs E_Dir -0.7179 | Improved |
| use numerical rank instead of MAD | oversmoothing metric · 7 node classification datasets | avg Pearson correlation with accuracy: 0.8374 vs 0.1601 | Improved |
| Erank vs NumRank choice across datasets (ablation) | rank-based metrics · Squirrel, Pubmed GAT, OGB-Arxiv GAT | correlation with accuracy: Squirrel GCN Erank 0.6316 vs NumRank 0.9582 | Mixed |
| deeper GCN (24 vs 2 layers) on Cora (ablation) | GCN · Cora | accuracy ratio 24 vs 2 layers: 0.2693 | Hurt |
Closest papers by meaning
- Graph Neural Networks Do Not Always Oversmooth (NeurIPS 2024 · similarity 0.92)
- A Signed Graph Approach to Understanding and Mitigating Oversmoothing (NeurIPS 2025 · similarity 0.90)
- A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks (ICML 2025 · similarity 0.88)
- Deep Hypergraph Neural Networks with Tight Framelets (AAAI 2025 · similarity 0.87)
- Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs (ICLR 2025 · similarity 0.87)
- Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing (NeurIPS 2026 · similarity 0.87)
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.
