AI Paper Atlas

Research map / Graph learning / GNN architectures

Learning Conjoint Attentions for Graph Neural Nets

Tiantian He, Yew-Soon Ong, L Bai

NeurIPS 2021 · Graph learning › GNN architectures · approach: GNN generalization theory · 1 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 matrix-factorization structural intervention to feature attention (CAT-I-MF)GAT-style graph attention · Cora node classificationAccuracy: 84.44 ± 0.19 -> 85.38 ± 0.16Improved
Add matrix-factorization structural intervention to feature attention (CAT-I-MF)GAT-style graph attention · Cite node classificationAccuracy: 72.38 ± 0.50 -> 73.22 ± 0.19Improved
Add matrix-factorization structural intervention to feature attention (CAT-I-MF)GAT-style graph attention · Pubmed node classificationAccuracy: 82.42 ± 0.04 -> 83.90 ± 0.24Improved
Add matrix-factorization structural intervention to feature attention (CAT-I-MF)GAT-style graph attention · CoauthorCS node classificationAccuracy: 93.60 ± 0.01 -> 93.74 ± 0.14Improved
Add matrix-factorization structural intervention to feature attention (CAT-I-MF)GAT-style graph attention · OGB-Arxiv node classificationAccuracy: 72.79 ± 0.09 -> 72.89 ± 0.06Improved
Add matrix-factorization structural intervention to feature attention (CAT-I-MF)GAT-style graph attention · Cora node clusteringAccuracy: 81.75 ± 0.26 -> 82.17 ± 0.11Improved
Add matrix-factorization structural intervention to feature attention (CAT-I-MF)GAT-style graph attention · Cite node clusteringAccuracy: 70.55 ± 0.85 -> 71.15 ± 0.12Improved
Add matrix-factorization structural intervention to feature attention (CAT-I-MF)GAT-style graph attention · Pubmed node clusteringAccuracy: 82.81 ± 0.32 -> 82.77 ± 0.07Hurt
Add matrix-factorization structural intervention to feature attention (CAT-I-MF)GAT-style graph attention · CoauthorCS node clusteringAccuracy: 90.16 ± 0.53 -> 90.26 ± 0.22Improved
Add matrix-factorization structural intervention to feature attention (CAT-I-MF)GAT-style graph attention · OGB-Arxiv node clusteringAccuracy: 76.91 ± 0.15 -> 77.72 ± 0.07Improved
Use structural-only attention (MF or SC) instead of feature-only attention (ablation)GAT attention · All node classification and clustering datasetsAccuracyMixed
Combine structural and feature correlations with implicit-direction weighting (ablation)CAT · Node classification and clusteringAccuracyImproved

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