---
title: "Revealing Concept Shift in Spatio-Temporal Graphs via State Learning"
authors:
  - "Kuo Yang"
  - "Yunhe Guo"
  - "Qihe Huang"
  - "Zhengyang Zhou"
  - "Yang Wang"
doi: "10.24963/ijcai.2025/392"
url: "https://ijcai.org/proceedings/2025/392"
pdf: "https://ijcai.org/proceedings/2025/0392.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "3525-3533"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Representation learning"
  - "Data Mining: DM: Networks"
  - "Data Mining: DM: Mining spatial and/or temporal data"
---

# Revealing Concept Shift in Spatio-Temporal Graphs via State Learning

Kuo Yang, Yunhe Guo, Qihe Huang, Zhengyang Zhou, Yang Wang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 3525-3533. DOI: [10.24963/ijcai.2025/392](https://doi.org/10.24963/ijcai.2025/392)

## Abstract

Dynamic graphs are ubiquitous in the real world, presenting the temporal evolution of individuals within spatial associations. Recently, dynamic graph learning research is flourishing, striving to more effectively capture evolutionary patterns and spatial correlations. However, existing methods still fail to address the issue of concept  shift in dynamic graphs. Concept  shift manifests as a distribution shift in the mapping pattern between historical observations and future evolution. The reason is that some environment variables in dynamic graphs exert varying effects on evolution patterns, but these variables are not effectively captured by the models, leading to the intractable concept shift issue. To tackle this issue, we propose a State-driven environment inference framework (Samen) to achieve a dynamic graph learning framework equipped with concept generalization ability. Firstly, we propose a two-stage environment inference and compression strategy. From the perspective of state space, we introduce a prefix-suffix collaborative state learning mechanism to bidirectionally model the spatio-temporal states. A hierarchical state compressor is further designed to refine the state information resulting in concept shift. Secondly, we propose a skip-connection spatio-temporal prediction module, which effectively utilizes the inferred environments to improve the model's generalization capability. Finally, we select seven datasets from different domains to validate the effectiveness of our model. By comparing the  performance of different models on samples with concept shift, we verify that our Samen gains generalization capacity that existing methods fail to capture.