AI Paper Atlas

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

TPAMI 2024 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 32 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
add the edge-splitting ES-layer (ablation)ES-GNN · Synthetic graphs (avg)accuracy (%): 75.4 -> 85.3Improved
add the edge-splitting ES-layer (ablation)ES-GNN · Synthetic graphs (homophily 0.3)accuracy (%): 53.3 -> 62.1Improved
add the edge-splitting ES-layer (ablation)ES-GNN · Synthetic graphs (homophily 0.1)accuracy (%): 84.6 -> 90.0Improved
add the edge-splitting ES-layer (ablation)ES-GNN · Synthetic graphs (homophily 0.9)accuracy (%): 96.7 -> 100.0Improved
use ES-GNN instead of ACM-GCN on SquirrelACM-GCN · Squirrelaccuracy (%): 67.0 -> 62.4Hurt
use ES-GNN instead of GloGNN++GloGNN++ · Texasaccuracy (%): 81.4 -> 82.3Improved
use ES-GNN instead of GCNGCN · Wisconsinaccuracy (%): 59.5 -> 85.3Improved
use ES-GNN instead of GCNGCN · Coraaccuracy (%): 79.7 -> 83.0Improved
use ES-GNN under injected fake edgesGCN/GAT · Perturbed homophilic graphsaccuracy (%)Improved
use ES-GNN on Cora under injected fake edgesbaselines · Perturbed Coraaccuracy (%)No clear effect

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