AI Paper Atlas

Research map / Graph learning / GNN architectures

From Node Interaction To Hop Interaction: New Effective and Scalable Graph Learning Paradigm

Jie Chen, Zilong Li, Yin Zhu, Junping Zhang, Jian Pu

CVPR 2023 · Graph learning › GNN architectures · approach: Structural GNN variants · 26 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 nonlinear interaction among precomputed hop features (ablation)HopGNN · Heterophily datasets (average)test accuracy: 65.59 -> 69.63Improved
Add nonlinear interaction among precomputed hop features (ablation)HopGNN · Homophily datasets (average)test accuracy: 84.35 -> 84.42No clear effect
Add hop-order embedding (ablation)HopGNN · Heterophily datasets (average)test accuracy: 60.93 -> 69.63Improved
Add hop-order embedding (ablation)HopGNN · Homophily datasets (average)test accuracy: 83.96 -> 84.42No clear effect
Replace mean fusion with attention fusion (ablation)HopGNN · Heterophily and homophily datasets (averages)test accuracy: 69.63 -> 69.81; 84.42 -> 84.60No clear effect
Replace mean fusion with max fusion (ablation)HopGNN · Heterophily and homophily datasets (averages)test accuracy: 69.63 -> 69.50; 84.42 -> 84.39No clear effect
Replace attention hop interaction with MLP (ablation)HopGNN · Heterophily datasets (average)test accuracy: 69.63 -> 67.21Hurt
Replace attention hop interaction with GCN (ablation)HopGNN · Heterophily datasets (average)test accuracy: 69.63 -> 68.18Hurt
Replace attention hop interaction with SAGE (ablation)HopGNN · Heterophily and homophily datasets (averages)test accuracy: 69.63 -> 69.11; 84.42 -> 84.45Mixed
Add feature-level self-supervised learningHopGNN · 9 homophily and heterophily datasets (Avg)test accuracy: 74.56 -> 75.53Improved
Use supervised contrastive learningHopGNN · 9 homophily and heterophily datasets (Avg)test accuracy: 74.56 -> 74.76No 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