AI Paper Atlas

Research map / Graph learning / GNN architectures

Expressivity-Preserving GNN Simulation

Fabian Jogl, Maximilian Thiessen, Thomas Gärtner

NeurIPS 2023 · Graph learning › GNN architectures · approach: Expressive equivariant message passing · 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 DS graph transformation to GINGIN · CSLaccuracy: 0.1 ± 0.0 -> 1.0 ± 0.0Improved
add DSS graph transformation to GINGIN · CSLaccuracy: 0.1 ± 0.0 -> 1.0 ± 0.0Improved
add CWN graph transformation to GINGIN · CSLaccuracy: 0.1 ± 0.0 -> 1.0 ± 0.0Improved
DS transformation + GIN vs DS non-standard message passingDS + GIN · 10 real-life datasetsfraction of datasets won: 60%Improved
DS transformation + GCN vs DS non-standard message passingDS + GCN · 10 real-life datasetsfraction of datasets won: 30%Hurt
DSS transformation + GIN vs DSS non-standard message passingDSS + GIN · 10 real-life datasetsfraction of datasets won: 60%Improved
DSS transformation + GCN vs DSS non-standard message passingDSS + GCN · 10 real-life datasetsfraction of datasets won: 30%Hurt
CWN transformation + GIN vs CWN non-standard message passingCWN + GIN · 10 real-life datasetsfraction of datasets won: 50%No clear effect
CWN transformation + GCN vs CWN non-standard message passingCWN + GCN · 10 real-life datasetsfraction of datasets won: 30%Hurt
add graph transformations (DS, DSS) to MPNN baselinesGIN/GCN · 10 real-life datasetsfraction of datasets beating MPNN: 70%Improved
add CWN transformation to GCNGCN · 10 real-life datasetsfraction of datasets beating MPNN: 50%No clear effect
use graph transformations with GIN vs GCNDSS + GIN · 10 real-life datasetsfraction of datasets with best model: 30%Improved

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