AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction

AAAI 2019 · Graph learning › Knowledge and temporal graphs · approach: Spatio-temporal graph traffic forecasting · 83 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
add STG2Vec graph embedding to temporal LSTM (ablation)Temporal LSTM · Citi-Bike check-inRMSE: 1.4960 -> 1.4265Helped
add weather features to temporal LSTM (ablation)Temporal LSTM · Citi-Bike check-inRMSE: 1.4960 -> 1.4884Helped
add attention to graph embedding (ablation)Temporal + Graph · Citi-Bike check-inRMSE: 1.4265 -> 1.4195Helped
add attention to graph embedding (ablation)Temporal + Graph · Citi-Bike check-outMAE: 0.7702 -> 0.7705No clear effect
add weather to temporal + attn-graph (full CE-LSTM) (ablation)Temporal + Attn-Graph · Citi-Bike check-outRMSE: 1.3173 -> 1.3115Helped
replace dynamic STG2Vec with static DeepWalk embedding in CE-LSTM (ablation)CE-LSTM · Citi-Bike check-inRMSE: 1.4138 -> 1.4337Hurt
replace dynamic STG2Vec with static spectral embedding in CE-LSTM (ablation)CE-LSTM · Citi-Bike check-inRMSE: 1.4138 -> 1.4449Hurt

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