State Feedback Enhanced Graph Differential Equations for Multivariate Time Series Forecasting

Cui, Jiaxu; Wang, Qipeng; Zhao, Yiming; Sun, Bingyi; Wang, Pengfei; Yang, Bo

doi:10.24963/ijcai.2025/820

State Feedback Enhanced Graph Differential Equations for Multivariate Time Series Forecasting

Jiaxu Cui, Qipeng Wang, Yiming Zhao, Bingyi Sun, Pengfei Wang, Bo Yang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 7374-7382.

https://doi.org/10.24963/ijcai.2025/820

Keywords

Machine Learning: ML: Time series and data streams
Data Mining: DM: Mining spatial and/or temporal data
Multidisciplinary Topics and Applications: MTA: Web and social networks

Abstract

Multivariate time series forecasting holds significant theoretical and practical importance in various fields, including web analytics and transportation. Recently, graph neural networks and graph differential equations have shown exceptional capabilities in modeling spatio-temporal features. However, existing methods often suffer from over-smoothing, hindering real-world problem-solving. In this work, we analyze the graph propagation process as a dynamical system and propose a novel feedback mechanism to enhance representation power, adaptively adjusting the representations to align with desired performance outcomes, thereby fundamentally mitigating the issue of over-smoothing. Moreover, we introduce an effective multivariate time series forecasting model called SF-GDE, based on the proposed graph propagation with the feedback mechanism. Intensive experiments are conducted on three real-world datasets from diverse fields. Results show that SF-GDE outperforms the state of the arts, and the feedback mechanism can serve as a universal booster to improve performance for graph propagation models.

Jiaxu Cui, Qipeng Wang, Yiming Zhao, Bingyi Sun, Pengfei Wang, and Bo Yang. 2025. State Feedback Enhanced Graph Differential Equations for Multivariate Time Series Forecasting. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 7374–7382. https://doi.org/10.24963/ijcai.2025/820

@inproceedings{ijcai2025p820,
  title     = {State Feedback Enhanced Graph Differential Equations for Multivariate Time Series Forecasting},
  author    = {Cui, Jiaxu and Wang, Qipeng and Zhao, Yiming and Sun, Bingyi and Wang, Pengfei and Yang, Bo},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {7374--7382},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/820},
  url       = {https://doi.org/10.24963/ijcai.2025/820},
}

TY  - CPAPER
TI  - State Feedback Enhanced Graph Differential Equations for Multivariate Time Series Forecasting
AU  - Cui, Jiaxu
AU  - Wang, Qipeng
AU  - Zhao, Yiming
AU  - Sun, Bingyi
AU  - Wang, Pengfei
AU  - Yang, Bo
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 7374
EP  - 7382
DO  - 10.24963/ijcai.2025/820
UR  - https://doi.org/10.24963/ijcai.2025/820
ER  -