atlas

Research map / Graph learning / GNN architectures

What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding

NeurIPS 2023 · Graph learning › GNN architectures · approach: Weisfeiler-Leman expressivity hierarchies · 6 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 graph-size renormalization to distance-encoding PE (ablation)GNN with distance-encoding PE · IMDB-BINARYtest accuracy: 63.95 -> 71.10Helped
add sqrt(n) renormalization to eigenvector PE (ablation)GNN with eigenvector PE · IMDB-BINARYtest accuracy: 66.10 -> 67.80Helped
add sqrt(n) renormalization to eigenvector PE (ablation)GNN with eigenvector PE · COLLABtest accuracy: 74.77 -> 73.74Hurt
add n renormalization to distance-encoding PE (ablation)GNN with distance-encoding PE · COLLABtest accuracy: 75.02 -> 75.65No clear effect
add renormalization of PEs by graph size (ablation)GNN with eigenvector PE on synthetic graphs of varied sizes · synthetic regression with larger test graphstest errorHelped

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