AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction

Yansong Ning, Hao Liu, Hao Henry Wang, Zhenyu Zeng, Hui Xiong

NeurIPS 2023 · Graph learning › Knowledge and temporal graphs · approach: Temporal knowledge graph reasoning · 13 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 non-Euclidean (hyperbolic/spherical) instead of Euclidean KG embeddings (ablation)UrbanKG embedding · NYC link predictionMRR: .516 -> .545Improved
use product-space embedding (GIE) instead of single hyperbolic space (best MuRP) (ablation)UrbanKG embedding · NYC link predictionMRR: .545 -> .573Improved
use product-space embedding (GIE) instead of single hyperbolic space (best MuRP) (ablation)UrbanKG embedding · CHI link predictionMRR: .519 -> .552Improved
use complex-space embeddings (RotatE, ComplEx, QuatE) instead of other Euclidean models (ablation)UrbanKG embedding · NYC link predictionMRR: .507 -> .274Hurt
concatenate product-space UrbanKG embeddings to STGCN inputSTGCN · NYC TaxiMAE/RMSE: 0.835/2.069 -> 0.781/1.942Improved
concatenate product-space UrbanKG embeddings to MTGNN inputMTGNN · NYC TaxiMAE/RMSE: 1.289/2.275 -> 1.183/2.118Improved
concatenate product-space UrbanKG embeddings to AGCRN inputAGCRN · NYC CrimeMicro/Macro-F1: 65.98/60.62 -> 67.75/61.88Improved
concatenate product-space UrbanKG embeddings to HGCN inputHGCN · CHI MobilityMAE/RMSE: 0.661/1.277 -> 0.637/1.146Improved
add UrbanKG embeddings from any space (vs none) (ablation)USTP models · NYC Taxi and CrimeMAE / F1Improved
use product-space embedding instead of Euclidean/hyperbolic/spherical embedding for downstream USTP (ablation)USTP models · NYC Taxi and CrimeMAE / F1Improved
increase product embedding dimension beyond 32 (ablation)ASTGCN with UrbanKG embedding · NYC Taxi and CrimeMAE / F1No clear effect
raise embedding dimension from 32 to 150 for link prediction (ablation)GIE · NYC link predictionMRR: .573 -> .587Improved

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