atlas

Research map / Graph learning / GNN architectures

Deep and Flexible Graph Neural Architecture Search

ICML 2022 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 3 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Search flexible propagation/transformation pipelines and their depths (ablation)DFG-NAS · Cora, Citeseer, PubMed, ogbn-arxivaccuracy: 1.1\% to 2.3\%Helped
Add node-adaptive Gate aggregation over propagation outputs (ablation)DFG-NAS · Cora, Citeseer, PubMed, ogbn-arxivaccuracy: 3.0-3.8\%Helped
Include Gate in the architecture search space (ablation)DFG-NAS · Cora, Citeseer, PubMed, ogbn-arxivaccuracy: 0.8-1.8\%Helped
Allow flexible P/T ordering instead of restricting pipelines to one pattern (ablation)DFG-NAS · Cora, Citeseer, PubMed, ogbn-arxivaccuracy: 1.1\% to 2.3\%Helped
Add skip connections to transformation operations (ablation)DFG-NAS · Cora, Citeseer, PubMedaccuracyHelped
Use alternating P and T rather than a flexible pipeline (ablation)DFG-NAS · Cora, Citeseer, PubMed, ogbn-arxivaccuracyHurt

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