AI Paper Atlas

Research map / Graph learning / GNN architectures

Pure Transformers are Powerful Graph Learners

Jinwoo Kim, Dat Tien Nguyen, Seonwoo Min, Sungjun Cho, Moontae Lee, Honglak Lee, Seunghoon Hong

NeurIPS 2022 · Graph learning › GNN architectures · approach: Expressive equivariant message passing · 56 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 node and type identifiers to node and edge tokens (ablation)Standard Transformer · PCQM4Mv2 validationMAE: 0.2340 -> 0.0910Improved
Use Laplacian eigenvectors instead of ORF node identifiers (ablation)TokenGT · PCQM4Mv2 validationMAE: 0.0962 -> 0.0910Improved
Use Performer kernel attention (ablation)TokenGT (Lap) · PCQM4Mv2 validationMAE: 0.0910 -> 0.0935Hurt
Add type identifiers (ablation)Transformer self-attention · Second-order equivariant basis approximation, dense input testL2 error: 53.93 ± 1.426 -> 40.06 ± 1.202Improved
Add node identifiers while retaining type identifiers (ablation)Transformer self-attention · Second-order equivariant basis approximation, dense input testL2 error: 40.06 ± 1.202 -> 0.009 ± 5e-5Improved
Use orthonormal node identifiers rather than independent first-order random embeddings (ablation)Transformer self-attention with type identifiers · Second-order equivariant basis approximation, dense input testL2 error: 32.49 ± 3.687 -> 0.009 ± 5e-5Improved
Use Laplacian eigenvectors instead of ORF node identifiers (ablation)Transformer self-attention with type identifiers · Second-order equivariant basis approximation, dense input testL2 error: 0.009 ± 5e-5 -> 0.005 ± 1e-4Improved
Use TokenGT (ORF)PCQM4Mv2 graph regression · PCQM4Mv2 validationMAE: 0.1083 -> 0.0962Improved
Use TokenGT (Lap)PCQM4Mv2 graph regression · PCQM4Mv2 validationMAE: 0.0864 -> 0.0910Hurt

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