AI Paper Atlas

Research map / Graph learning / GNN architectures

Optimality of Message-Passing Architectures for Sparse Graphs

Aseem Baranwal, Kimon Fountoulakis, Aukosh Jagannath

NeurIPS 2023 · Graph learning › GNN architectures · approach: Expressive equivariant message passing · 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 Architecture 1 (Bayes-optimal local classifier) instead of vanilla GCN or MLPArchitecture 1 · CSBM n=10000, d=4, binarytest accuracyImproved
Set graph signal Γ=0 or Γ=1 (extreme graph signals)Architecture 1 · CSBM n=10000, d=4test accuracyNo clear effect
Increase AMP-BP iterations from t=5 to t=20 (ablation)AMP-BP · CSBM n=1000, γ=1, d=5accuracy: 0.753 -> 0.858 (Γ=0.3)Improved
Increase AMP-BP iterations from t=5 to t=20 (ablation)AMP-BP · CSBM n=1000, γ=1, d=500accuracy: 0.554 -> 0.848 (Γ=0.3)Improved
Architecture 1 versus AMP-BP t=20 in low dimension with strong featuresArchitecture 1 · CSBM n=1000, γ=1, d=5accuracy: 0.870 vs 0.858 (Γ=0.3); 0.996 vs 0.952 (Γ=0.6)Improved
Architecture 1 versus AMP-BP t=20 in high dimension with strong featuresArchitecture 1 · CSBM n=1000, γ=1, d=500accuracy: 0.995 vs 0.877 (Γ=0.4); 0.998 vs 0.940 (Γ=0.6)Improved
Weaken feature signal from γ=1 to γ=0.2 in high dimension (d=500)Architecture 1 vs AMP-BP t=20 · CSBM n=1000, d=500accuracy: 0.762 vs 0.804 (Γ=0.5); 0.788 vs 0.878 (Γ=0.6)Hurt
Weaken feature signal to γ=0.2 in low dimension (d=5)Architecture 1 vs AMP-BP t=20 · CSBM n=1000, γ=0.2, d=5accuracy: 0.554 vs 0.579 (Γ=0.3); 0.997 vs 0.880 (Γ=0.6)Mixed
Random parameter initialization with gradient descentArchitecture 1 · CSBM binary, Γ=0.2parameter convergence to ansatzImproved

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