4 papers
MixTTE: Multi-Level Mixture-of-Experts for Scalable and Adaptive Travel Time Estimation
Wenzhao Jiang, Jindong Han, Ruiqian Han +1
Accurate Travel Time Estimation (TTE) is critical for ride-hailing platforms, where errors directly impact user experience and operational efficiency. While existing production sys…
SDE: A Simplified and Disentangled Dependency Encoding Framework for State Space Models in Time Series Forecasting
Zixuan Weng, Jindong Han, Wenzhao Jiang +1
In recent years, advancements in deep learning have spurred the development of numerous models for Long-term Time Series Forecasting (LTSF). However, most existing approaches strug…
When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlook
Wenzhao Jiang, Hao Liu, Hui Xiong
Graph Neural Networks (GNNs) have emerged as powerful representation learning tools for capturing complex dependencies within diverse graph-structured data. Despite their success i…
Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction
Wenzhao Jiang, Jindong Han, Hao Liu +3
Rapid urbanization has significantly escalated traffic congestion, underscoring the need for advanced congestion prediction services to bolster intelligent transportation systems.…