AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Graph Tokenization for Bridging Graphs and Transformers

Zeyuan Guo, Enmao Diao, Cheng Yang, Chuan Shi

ICLR 2026 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 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
add BPE on top of Feuler serialization (ablation)GT+GTE · ogbg-molhivROC-AUC: 81.3 -> 87.4Improved
add BPE on top of Feuler serialization (ablation)GT+GTE · ZINCMAE: 0.171 -> 0.131Improved
add BPE on top of Feuler serialization (ablation)GT+GTE · QM9MAE: 0.088 -> 0.071Improved
add BPE on top of Feuler serialization (ablation)GT+GTE · COIL-DELaccuracy: 85.6 -> 88.0Improved
add BPE to BFS serialization (ablation)GT+GTE · ogbg-molhivROC-AUC: 81.2 -> 72.3Hurt
add BPE to BFS serialization (ablation)GT+GTE · ZINCMAE: 0.696 -> 0.453Improved
use Feuler (frequency-guided Eulerian) instead of unguided Eulerian (ablation)GT+GTE · ogbg-molhivROC-AUC: 84.5 -> 87.4Improved
use reversible Eulerian-type serialization instead of BFS (ablation)GT+GTE · ZINCMAE: 0.453 -> 0.131Improved
use frequency-guided CPP (FCPP) instead of CPP (ablation)GT+GTE · ogbg-molhivROC-AUC: 86.9 -> 86.4No clear effect
scale backbone from BERT-small to GTEGraphTokenizer · ogbg-molhivROC-AUC: 82.6 -> 87.4Improved
GT+GTE vs best GNN baselineGraphTokenizer · COIL-DELaccuracy: 91.5 -> 89.6Hurt
GT+BERT vs GCN+GraphTokenizer · ZINCMAE: 0.116 -> 0.241Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

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