AI Paper Atlas

Research map / Graph learning / GNN architectures

PlanE: Representation Learning over Planar Graphs

Radoslav Dimitrov, Zeyang Zhao, Ralph Abboud, Ismail Ilkan Ceylan

NeurIPS 2023 · Graph learning › GNN architectures · approach: Theory of graph convolutional networks · 1 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 planar decomposition (BasePlanE) instead of standard GCNmessage passing GNN · EXPaccuracy (%): 50.0 -> 100Improved
BasePlanE instead of random-node-initialized GCNGCN-RNI(N) · EXPaccuracy (%): 98.0 -> 100Improved
BasePlanE instead of GINGIN · P3Raccuracy (%): 11.1 -> 100Improved
BasePlanE instead of 2-WL expressive PPGNPPGN · P3Raccuracy (%): 100 -> 100No clear effect
BasePlanE instead of GINGIN · QM9_CCMAE: 0.0612 -> 0.0023Improved
BasePlanE instead of ESANESAN · QM9_CCMAE: 0.0038 -> 0.0023Improved
GCN instead of constant predictionconstant baseline · QM9_CCMAE: 0.1627 -> 0.1275Improved
E-BasePlanE instead of GINGIN · MolHIVROC-AUC: 77.07 -> 80.04Improved
E-BasePlanE instead of CINCIN · MolHIVROC-AUC: 80.94 -> 80.04No clear effect
E-BasePlanE instead of R-SPN k=10R-SPN · QM9 muMAE: 2.21 -> 1.97Improved
E-BasePlanE instead of R-SPN k=10R-SPN · QM9 ZPVEMAE: 2.58 -> 2.81Hurt
E-BasePlanE instead of R-SPN k=10R-SPN · QM9 GMAE: 0.83 -> 0.88Hurt

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