activity
20242026
collaborators

6 papers

cs.LG2026

A2TTA: Anchored-and-Agile Test-Time Adaptation for Evolving Traffic Sensor Networks

Du Yin, Xiachong Lin, Yue Tan +4

Traffic forecasting is important for efficient traffic management and route planning in smart cities. Existing traffic forecasting studies typically assume fixed sensor graphs, ove…

cs.LG2025

AutoSTF: Decoupled Neural Architecture Search for Cost-Effective Automated Spatio-Temporal Forecasting

Tengfei Lyu, Weijia Zhang, Jinliang Deng +1

Spatio-temporal forecasting is a critical component of various smart city applications, such as transportation optimization, energy management, and socio-economic analysis. Recentl…

cs.LG2024

Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting

Jinliang Deng, Feiyang Ye, Du Yin +3

Long-term time series forecasting (LTSF) represents a critical frontier in time series analysis, characterized by extensive input sequences, as opposed to the shorter spans typical…

cs.LG2024

Enhancing Spatio-temporal Quantile Forecasting with Curriculum Learning: Lessons Learned

Du Yin, Jinliang Deng, Shuang Ao +6

Training models on spatio-temporal (ST) data poses an open problem due to the complicated and diverse nature of the data itself, and it is challenging to ensure the model's perform…

cs.LG2024

Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting

Zheng Dong, Renhe Jiang, Haotian Gao +4

Spatiotemporal time series forecasting plays a key role in a wide range of real-world applications. While significant progress has been made in this area, fully capturing and lever…

cs.LG2024

Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting

Haotian Gao, Renhe Jiang, Zheng Dong +3

Spatiotemporal forecasting techniques are significant for various domains such as transportation, energy, and weather. Accurate prediction of spatiotemporal series remains challeng…