AI Paper Atlas

Research map / Graph learning / GNN architectures

Neural Graph Embedding for Neural Architecture Search

Wei Li, Shaogang Gong, Xiatian Zhu

AAAI 2020 · Graph learning › GNN architectures · approach: GNN generalization theory · 26 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 plain learned embedding for operation probabilities (ablation)DARTS-style baseline · CIFAR-10test error (%): 3.44 -> 3.14Improved
add RNN modelling of node relationships on top of plain embedding (ablation)plain embedding · CIFAR-10test error (%): 3.14 -> 2.71Improved
replace RNN with 3-layer GCN neural graph embedding (ablation)NGE · CIFAR-10test error (%): 2.71 -> 2.60Improved
replace RNN with GCN neural graph embedding (ablation)NGE · CIFAR-100test error (%): 16.97 -> 16.53Improved
add plain embedding to baseline (ablation)DARTS-style baseline · CIFAR-100test error (%): 17.90 -> 17.60Improved
use NGE instead of GHN graph-based searchgraph-based NAS · CIFAR-10test error (%): 2.84 -> 2.60Improved
NGE cell searched on CIFAR-10 transferred to ImageNet vs DARTSNGE · ImageNet mobiletop-1 error (%): 26.7 -> 25.3Improved
NGE vs ProxylessNAS-G on CIFAR-10NGE · CIFAR-10test error (%): 2.08 -> 2.60Hurt

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