Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Causal invariant geographic network representations with feature and structural distribution shifts
Yuhan Wang, Silu He, Qinyao Luo +4
The existing methods learn geographic network representations through deep graph neural networks (GNNs) based on the i.i.d. assumption. However, the spatial heterogeneity and tempo…
cs.LG2024
CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph
Silu He, Qinyao Luo, Xinsha Fu +3
Local Attention-guided Message Passing Mechanism (LAMP) adopted in Graph Attention Networks (GATs) is designed to adaptively learn the importance of neighboring nodes for better lo…
cs.LG2024
LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
Qinyao Luo, Silu He, Xing Han +2
Accurate traffic forecasting is a fundamental problem in intelligent transportation systems and learning long-range traffic representations with key information through spatiotempo…