AI Paper Atlas

Research map / Graph learning / GNN architectures

Graph Neural Networks are Dynamic Programmers

Andrew Joseph Dudzik, Petar Veličković

NeurIPS 2022 · Graph learning › GNN architectures · approach: Theory of graph convolutional networks · 8 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
Add order-3 messages and edge updatesMPNN · CLRS six tasks OOD, large modelsaccuracy: 35.24% -> 39.43%Improved
Add order-3 messages and edge updatesMPNN · CLRS six tasks OOD, small modelsaccuracy: 33.57% -> 36.23%Mixed
Add order-3 messages and edge updatesPGN · CLRS edge-centric tasks OODaccuracy: 35.03% -> 39.08%; 4.44% ± 1.06Improved
Add order-3 messages and edge updatesPGN · CLRS other tasks OODaccuracy: 35.37% -> 36.33%; 1.01% ± 0.11Improved
Add order-3 messages and edge updatesPGN · CLRS 27 tasks OODaccuracy: 35.20% -> 37.70%Improved
Add order-3 messages and edge updatesPGN · Bellman-Ford, CLRS OODaccuracy: 80.05% ± 0.87 -> 77.69% ± 0.78Hurt
Add order-3 messages and edge updatesPGN · Floyd-Warshall, CLRS OODaccuracy: 8.01% ± 1.31 -> 17.31% ± 0.92Improved
Add order-3 messages and edge updatesPGN · LCS Length, CLRS OODaccuracy: 52.87% ± 2.35 -> 67.24% ± 4.93Improved
Add order-3 messages and edge updatesMPNN · Floyd-Warshall, CLRS OODaccuracy: 7.46% ± 0.63 -> 9.00% ± 0.81Improved

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