Tracking Topological Shifts: How Can Dynamic Graph Invariant Learning Enable Reliable Out-of-Time Spatio-Temporal Prediction?

Hao, Xinyan; Wan, Huaiyu; Guo, Shengnan; Wang, Shaojiang; Lin, Youfang

doi:10.24963/ijcai.2026/296

Tracking Topological Shifts: How Can Dynamic Graph Invariant Learning Enable Reliable Out-of-Time Spatio-Temporal Prediction?

Xinyan Hao, Huaiyu Wan, Shengnan Guo, Shaojiang Wang, Youfang Lin

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 2662-2670.

https://doi.org/10.24963/ijcai.2026/296

Keywords

Data Mining: Mining spatial and/or temporal data

Abstract

Spatio-temporal graph networks form the foundation of modern traffic prediction, yet their deployment is fundamentally challenged by the pervasive reality of distribution shifts. While out-of-distribution (OOD) learning holds promise for robustness, existing methods rely on static graph structures, failing to capture the inherent topological dynamics of real-world traffic systems and thus limiting long-term deployment reliability. To bridge this gap, we propose DynaSTar, a Dynamic Spatio-Temporal Graph Invariant Learning model designed for reliable out-of-time (OOT) traffic prediction under evolving topologies. Our model employs a dynamic probabilistic graph structure, which is continuously refined through momentum-based updates and differentiable sparse sampling to model evolving inter-node dependencies. Besides, it utilizes node-level environment construction and modulated prediction to extract representations invariant to heterogeneous neighborhood fluctuations, enabling robust generalization. Comprehensive experiments on large-scale, long-term real-world datasets demonstrate that by effectively tracking evolving topological shifts, DynaSTar consistently outperforms state-of-the-art baselines across various OOT scenarios.

Xinyan Hao, Huaiyu Wan, Shengnan Guo, Shaojiang Wang, and Youfang Lin. 2026. Tracking Topological Shifts: How Can Dynamic Graph Invariant Learning Enable Reliable Out-of-Time Spatio-Temporal Prediction?. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 2662–2670. https://doi.org/10.24963/ijcai.2026/296

@inproceedings{ijcai2026p296,
  title     = {Tracking Topological Shifts: How Can Dynamic Graph Invariant Learning Enable Reliable Out-of-Time Spatio-Temporal Prediction?},
  author    = {Hao, Xinyan and Wan, Huaiyu and Guo, Shengnan and Wang, Shaojiang and Lin, Youfang},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {2662--2670},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/296},
  url       = {https://doi.org/10.24963/ijcai.2026/296},
}

TY  - CPAPER
TI  - Tracking Topological Shifts: How Can Dynamic Graph Invariant Learning Enable Reliable Out-of-Time Spatio-Temporal Prediction?
AU  - Hao, Xinyan
AU  - Wan, Huaiyu
AU  - Guo, Shengnan
AU  - Wang, Shaojiang
AU  - Lin, Youfang
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 2662
EP  - 2670
DO  - 10.24963/ijcai.2026/296
UR  - https://doi.org/10.24963/ijcai.2026/296
ER  -