AI Paper Atlas

Research map / Graph learning / GNN architectures

Are GATs Out of Balance?

Nimrah Mustafa, Aleksandar Bojchevski, Rebekka Burkholz

NeurIPS 2023 · Graph learning › GNN architectures · approach: GNN generalization theory · 0 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
use balanced LL-orthogonal initialization instead of XavierGAT, 10 layers · Cora (SGD)test accuracy: 39.3% -> 80.2%Improved
use balanced LL-orthogonal initialization instead of XavierGAT, 5 layers · Cora (SGD)test accuracy: 75.5% -> 79.9%Improved
use balanced LL-orthogonal initialization instead of XavierGAT, 40 layers · Citeseer (SGD)test accuracy: 18.72 ± 1.15 -> 63.40 ± 1.43Improved
use balanced Xavier initialization instead of XavierGAT, 10 layers · Citeseer (SGD)test accuracy: 24.70 ± 8.90 -> 64.13 ± 1.57Improved
increase width from 64 to 512 with Xavier init (ablation)GAT, 10 layers · Cora (SGD)test accuracy: 24.7% -> 68.7%Improved
increase width from 64 to 512 with Bal_O init (ablation)GAT, 10 layers · Cora (SGD)test accuracy: 79.7% -> 80.9%Improved
replace ReLU with ELU under Bal_O (ablation)GAT, 10 layers Bal_O · Cora (SGD)test accuracy: 79.46 ± 1.34 -> 47.76 ± 7.39Hurt
add dropout 0.6 to balanced Bal_O (ablation)GAT, 10 layers · Cora (SGD)test accuracy: 79.46 ± 1.34 -> 44.40 ± 1.84Hurt
add dropout 0.6 to Xavier GAT with Adam (ablation)GAT, 10 layers Xavier · Cora (Adam)test accuracy: 70.86 ± 3.99 -> 32.48 ± 6.99Hurt
add weight decay 0.0005 to Xavier GAT with SGD (ablation)GAT, 10 layers Xavier · Cora (SGD)test accuracy: 25.48 ± 18.13 -> 18.78 ± 11.96No clear effect
use 8 attention heads instead of 1 with Bal_O (ablation)GAT, 10 layers Bal_O · Cora (SGD)test accuracy: 79.46 ± 1.34 -> 79.06 ± 0.73No clear effect
turn off weight sharing with Bal_O (ablation)GAT, 10 layers Bal_O · Cora (SGD)test accuracy: 79.46 ± 1.34 -> 79.06 ± 0.32No 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