AI Paper Atlas

Research map / Graph learning / GNN architectures

GOAT: A Global Transformer on Large-scale Graphs

Kezhi Kong, Jiuhai Chen, John Kirchenbauer, Renkun Ni, C. Bayan Bruss, Tom Goldstein

ICML 2023 · Graph learning › GNN architectures · approach: Simple and scalable GNNs

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
adding the local attention module (GOAT vs local-only removed global) (ablation)GOAT · arxiv-yearvalidation accuracy: ~3% boostImproved
removing the global attention module (local-only) (ablation)GOAT · ogbn-arxivvalidation accuracyNo clear effect
increasing codebook size from 512 to 4k (ablation)GOAT · arxiv-yearaccuracy: 50.90 to 53.57Improved
increasing codebook size from 512 to 4k (ablation)GOAT · ogbn-arxivaccuracy: 71.92 to 72.41Improved
layer norm instead of batch norm (ablation)GOAT · ogbn-arxivvalidation accuracyNo clear effect
removing normalization entirely (ablation)GOAT · ogbn-arxiv and arxiv-yearvalidation accuracyHurt
GOAT global-only variant vs GAT-NS on training speedGOAT-Global-only · ogbn-productsseconds per epoch (batch 1k): 5.58 vs 127.42 for GATImproved
full GOAT (local + global) vs GAT-NS on training timeGOAT · ogbn-productsseconds per epoch (batch 1k): 109.51 vs 127.42 for GATMixed
GOAT vs LINKX/MixHop baselines on heterophilous and homophilous dataGOAT · snap-patents (random 50%)accuracy: 54.97 vs LINKX 60.12Mixed

Later papers that compared with this method

5 later accepted papers report GOAT as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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