AI Paper Atlas

Research map / Graph learning / GNN architectures

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

Vignesh Kothapalli, Tom Tirer, Joan Bruna

NeurIPS 2023 · Graph learning › GNN architectures · approach: GNN generalization theory · 2 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 trained GNN layers instead of projected power iteration on NLrandom-feature classifier · SSBM test graphsavg test overlap: 0.04 -> 1Improved
use trained GNN layers instead of projected power iteration on BHrandom-feature classifier · SSBM test graphsavg test overlap: 0.15 -> 1Improved
train GNN until zero training errorGNN psi_F and psi_F' · SSBM training graphsNC1 within-class variabilityImproved
GNN versus plain DNN on instance-wise dataGNN penultimate features · SSBMNC1 levelHurt
remove W1 (psi_F' vs psi_F) (ablation)GNN · SSBM test graphsdepthwise rate of NC1 decreaseImproved

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