AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

UrbanGraph: Physics-Informed Spatio-Temporal Dynamic Heterogeneous Graphs for Urban Microclimate Prediction

Weilin Xin, Chenyu Huang, Peilin Li, Jing Zhong, Jiawei Yao

ICLR 2026 · Graph learning › Knowledge and temporal graphs · approach: Continuous-time dynamic graph learning

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 heterogeneous relation-specific message passing (RGCN) instead of homogeneous GCN (ablation)UrbanGraph · Ablation (hidden 384, single head)R2: 0.8336 -> 0.8629Improved
use dynamic time-varying graph instead of static graph (ablation)UrbanGraph · Ablation (hidden 384, single head)R2: 0.8057 -> 0.8629Improved
inject physics as hard graph topology rather than PINN soft loss (ablation)GCN+LSTM backbone · Physics injection strategy (GCN+LSTM backbone)Avg R2: 0.7876 -> 0.8542Improved
add PDE soft-constraint loss (ablation)GCN+LSTM · Physics injection strategy (GCN+LSTM backbone)Avg R2: 0.7846 -> 0.7876No clear effect
explicit causal pruning vs implicit recurrent dynamic graph (LRGCN)UrbanGraph vs LRGCN · UMC4/12 test set (avg over 6 variables), main comparison (hidden 128)Avg R2: 0.8422 -> 0.8542Improved
explicit causal pruning vs LRGCNUrbanGraph vs LRGCN · UMC4/12 test set (avg over 6 variables), main comparison (hidden 128)FLOPs: 3.49e10 -> 9.13e9Improved
use concatenation fusion instead of attention or multiplicative (ablation)UrbanGraph · Fusion strategyAvg R2: 0.8491/0.8515 -> 0.8542Improved
add LSTM temporal module (ablation)UrbanGraph · 12-hour horizonR2Improved
use single prediction head instead of multi-head (ablation)UrbanGraph · ablation settingR2Improved
add UrbanGraph vs STGCN efficiencyUrbanGraph vs STGCN · UMC4/12 test set (avg over 6 variables), main comparison (hidden 128)training time (s/epoch): 5.3547 -> 24.4823Hurt

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