AI Paper Atlas

Research map / Graph learning / GNN architectures

Are we measuring oversmoothing in graph neural networks correctly?

Kaicheng Zhang, Piero Deidda, Desmond Higham, Francesco Tudisco

ICLR 2026 · Graph learning › GNN architectures · approach: Expressive equivariant message passing · 12 citations (OpenAlex)

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 changedWhereMeasuredEffect
measure oversmoothing with effective rank instead of Dirichlet energyGCN/GAT oversmoothing metric · 7 node classification datasets, depth 2-24avg Pearson correlation with accuracy: Erank 0.9103 vs E_Dir -0.7179Improved
use numerical rank instead of MADoversmoothing metric · 7 node classification datasetsavg Pearson correlation with accuracy: 0.8374 vs 0.1601Improved
Erank vs NumRank choice across datasets (ablation)rank-based metrics · Squirrel, Pubmed GAT, OGB-Arxiv GATcorrelation with accuracy: Squirrel GCN Erank 0.6316 vs NumRank 0.9582Mixed
deeper GCN (24 vs 2 layers) on Cora (ablation)GCN · Coraaccuracy ratio 24 vs 2 layers: 0.2693Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy