AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

NASGEM: Neural Architecture Search via Graph Embedding Method

Hsin-Pai Cheng, Tunhou Zhang, Yixing Zhang, Shiyu Li, Feng Liang, Feng Yan, Meng Li, Vikas Chandra, Hai Li, Yiran Chen

AAAI 2021 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 14 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 kernel-guided graph embedding rather than an MLP autoencoder (ablation)NASGEM predictor · NASGEM-Bench, 10% training dataKendall's tau: 0.45 -> 0.48Improved
Use kernel-guided graph embedding rather than an MLP autoencoder (ablation)NASGEM predictor · NASGEM-Bench, 100% training dataKendall's tau: 0.47 -> 0.55Improved
Use kernel-guided graph embedding rather than an MLP autoencoder (ablation)NASGEM predictor · NASGEM-Bench, 10% training dataPearson correlation coefficient: 0.57 -> 0.76Improved
Use kernel-guided graph embedding rather than an MLP autoencoder (ablation)NASGEM predictor · NASGEM-Bench, 100% training dataPearson correlation coefficient: 0.71 -> 0.85Improved
Increase graph node count or reduce embedding dimension (ablation)NASGEM encoder · Generated graph pairs at varied node counts and embedding dimensionssimilarity lossHurt
Use kernel-guided graph embedding rather than an MLP autoencoderNASGEM predictor · ImageNettop-1 test error (%): 24.1 -> 23.3Improved
Use GEMNet-B rather than MnasNet×1.3 as the backboneRetinaNet · MS COCO minivalAP: 35.0 -> 35.7Improved
Use GEMNet-A rather than MnasNet×1.3 as the backboneFaster RCNN · MS COCO minivalAP: 35.4 -> 35.3Hurt
Use GEMNet-B rather than MnasNet×1.3 as the backboneFaster RCNN · MS COCO minivalAP: 35.4 -> 35.7Improved
Add graph-kernel guidance to the graph embedding (ablation)NASGEM predictor · NASBench-101predicted global accuracy: around 0.2%Improved

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