AI Paper Atlas

Research map / Graph learning / GNN architectures

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks

Keyulu Xu, Mozhi Zhang, Jingling Li, Simon Shaolei Du, Ken-Ichi Kawarabayashi, Stefanie Jegelka

ICLR 2021 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 110 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 max readout instead of sum readout (ablation)GNN for max degree · Max degree extrapolationMAPEImproved
Use min aggregation and min readout instead of sum-based operations (ablation)GNN for shortest path · Shortest path extrapolationMAPEImproved
Encode the force calculation in edge features (ablation)GNN for the n-body problem · n-body problem, unseen masses or distancesMAPEImproved
Train on graphs with varied rather than restricted degree structures (ablation)GNN with max readout · Max degree extrapolationMAPEImproved
Train on graphs with extremely sparse or dense structures (ablation)GNN with min operations · Shortest path extrapolationMAPEHurt
Use a training distribution covering all directions rather than restricted directions (ablation)ReLU MLP learning a linear target · Linear-function extrapolationExtrapolation errorImproved
Use ReLU MLPs to extrapolate nonlinear targets that are not nearly linear along directions from the originReLU MLP · Nonlinear function extrapolationExtrapolation errorHurt

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