---
title: "Tracking Topological Shifts: How Can Dynamic Graph Invariant Learning Enable Reliable Out-of-Time Spatio-Temporal Prediction?"
authors:
  - "Xinyan Hao"
  - "Huaiyu Wan"
  - "Shengnan Guo"
  - "Shaojiang Wang"
  - "Youfang Lin"
doi: "10.24963/ijcai.2026/296"
url: "https://ijcai.org/proceedings/2026/296"
pdf: "https://ijcai.org/proceedings/2026/0296.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "2662-2670"
track: "Main Track"
keywords:
  - "Data Mining: Mining spatial and/or temporal data"
---

# 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

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 2662-2670. DOI: [10.24963/ijcai.2026/296](https://doi.org/10.24963/ijcai.2026/296)

## 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.