AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction

Weilin Ruan, Xilin Dang, Ziyu Zhou, Sisuo Lyu, Yuxuan Liang

AAAI 2026 · Graph learning › Knowledge and temporal graphs · approach: Spatio-temporal graph traffic forecasting

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 the fusion query (query generator) (ablation)RAST · PEMS07MAE: 24.53 -> 19.52Improved
add ST-Retriever (ablation)RAST · PEMS07MAE: 21.71 -> 19.52Improved
add spatial encoder (ablation)RAST · PEMS07MAE: 22.88 -> 19.52Improved
add temporal encoder (ablation)RAST · PEMS07MAE: 23.66 -> 19.52Improved
add retrieval embedding to query embedding (cross-attention fusion) (ablation)RAST · PEMS07MAE: 23.59 -> 19.52Improved
fuse query with retrieval embedding instead of retrieval embedding alone (ablation)RAST · PEMS07MAE, RMSE, MAPE: MAE 19.38 vs 19.52; MAPE 13.32 vs 8.23Mixed
add MLP predictor (ablation)RAST · PEMS07MAE: 21.67 -> 19.52Improved
set retrieval store update interval to 10 epochs rather than 20 or 50 (ablation)RAST · PEMS04MAE, MAPEImproved
increase query embedding dimension from 32 to 128 (ablation)RAST · PEMS04MAEImproved
use more than 3 encoder layers (ablation)RAST · PEMS04MAE: MAE 19.19 at 3 layersNo clear effect
use RAST instead of STGCN for efficiencylarge-scale traffic forecasting · GBAtraining time per epoch (s): 852.57 -> 154.08Improved
RAST versus baselines on PEMS03RAST · PEMS03MAE, RMSE, MAPE: MAE 15.20 vs DSTAGNN 15.57Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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