FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts
Open Access
- 20 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1975-1986
Abstract
No abstract availableAll Related Versions
Funding Information
- National Natural Science Foundation of China (62362069)
- Yunnan Fundamental Research Projects (202401BF070001-024)
- Open Project Program of Yunnan Key Laboratory of Intelligent Systems and Computing (ISC24Y05)
This publication has 33 references indexed in Scilit:
- A Survey on Mixture of Experts in Large Language ModelsIEEE Transactions on Knowledge and Data Engineering, 2025
- Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity AnalysisIEEE Transactions on Knowledge and Data Engineering, 2024
- A Comprehensive Survey of Regression-Based Loss Functions for Time Series Forecasting2024
- SAGDFN: A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecasting2024
- Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2023
- Graph Neural Networks for Intelligent Transportation Systems: A SurveyIEEE Transactions on Intelligent Transportation Systems, 2023
- Spatial-Temporal Position-Aware Graph Convolution Networks for Traffic Flow ForecastingIEEE Transactions on Intelligent Transportation Systems, 2022
- Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic ForecastingIEEE Transactions on Knowledge and Data Engineering, 2021
- Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks2020
- The Approximation of One Matrix by Another of Lower RankPsychometrika, 1936