AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

GMAN: A Graph Multi-Attention Network for Traffic Prediction

AAAI 2020 · Graph learning › Knowledge and temporal graphs · approach: Spatio-temporal graph traffic forecasting · 1,722 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
Use GMAN instead of Graph WaveNetTraffic prediction · Xiamen, 1 hourMAE: 13.33 -> 12.79Helped
Use GMAN instead of Graph WaveNetTraffic prediction · PeMS, 1 hourMAE: 1.95 -> 1.86Helped
Use GMAN instead of Graph WaveNetTraffic prediction · Xiamen, 15 minMAE: 11.26 -> 11.50Hurt
Use GMAN instead of Graph WaveNetTraffic prediction · PeMS, 15 minMAE: 1.30 -> 1.34Hurt
Use GMAN instead of Graph WaveNetTraffic prediction · 30 min, Xiamen and PeMSMAE: 12.06 -> 12.02; 1.63 -> 1.62Helped
Add spatial attention (ablation)GMAN · Traffic prediction, per-step MAEMAEHelped
Add temporal attention (ablation)GMAN · Traffic prediction, per-step MAEMAEHelped
Add gated fusion (ablation)GMAN · Traffic prediction, per-step MAEMAEHelped
Add transform attention (ablation)GMAN · Traffic prediction, especially long-term horizonMAEHelped

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