AI Paper Atlas

Research map / Graph learning / GNN architectures

Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks

Pascal Esser, Leena Chennuru Vankadara, Debarghya Ghoshdastidar

NeurIPS 2021 · Graph learning › GNN architectures · approach: Oversmoothing and heterophily · 3 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
increase alignment between node features and graph (Gamma) in the planted SBMGNN transductive Rademacher bound · SBM and Cora (noise-simulated)generalisation errorHurt
increase graph size nGNN · SBM and Corageneralisation errorNo clear effect
increase number of observed labelled nodes mGNN · SBM and Corageneralisation errorImproved
increase depth K of vanilla GNNGNN · SBM and Corageneralisation errorHurt
add residual (GCNII-style initial-residual) connectionsGNN · SBM and Corageneralisation errorImproved

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