AI Paper Atlas

Research map / Graph learning / GNN architectures

Generalization and Representational Limits of Graph Neural Networks

Vikas Garg, Stefanie Jegelka, Tommi Jaakkola

ICML 2020 · Graph learning › GNN architectures · approach: Expressive equivariant message passing · 50 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 only local information in message passingLU-GNNs · Graph properties including girth, circumference, diameter, radius, cycles, and k-cliqueability to decide graph propertyHurt
Use consistent port numbering to order neighbor messagesCPNGNN · Graph discriminationability to distinguish graphsImproved
Change the consistent port orderingCPNGNN · Graph discriminationability to distinguish graphsMixed
Use local directional angles and distancesDimeNet · Graph discriminationability to decide graph propertiesImproved
Use only DimeNet's local angles and distancesDimeNet · Girth, circumference, diameter, radius, and total number of cyclesability to decide graph propertyHurt
Add port ordering and plane-based geometric features to directional messagesH-DCPN · Graph discriminationability to distinguish graphsImproved
Bound GNN complexity through local computation trees and account for local permutation invarianceGNN generalization analysis · Binary graph classificationgeneralization-bound tightnessImproved

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