---
title: "CAN-ST: Clustering Adaptive Normalization for Spatio-temporal OOD Learning"
authors:
  - "Min Yang"
  - "Yang An"
  - "Jinliang Deng"
  - "Xiaoyu Li"
  - "Bin Xu"
  - "Ji Zhong"
  - "Xiankai Lu"
  - "Yongshun Gong"
doi: "10.24963/ijcai.2025/394"
url: "https://ijcai.org/proceedings/2025/394"
pdf: "https://ijcai.org/proceedings/2025/0394.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "3543-3551"
track: "Main Track"
keywords:
  - "Data Mining: DM: Mining data streams"
  - "Data Mining: DM: Applications"
  - "Data Mining: DM: Mining spatial and/or temporal data"
---

# CAN-ST: Clustering Adaptive Normalization for Spatio-temporal OOD Learning

Min Yang, Yang An, Jinliang Deng, Xiaoyu Li, Bin Xu, Ji Zhong, Xiankai Lu, Yongshun Gong

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 3543-3551. DOI: [10.24963/ijcai.2025/394](https://doi.org/10.24963/ijcai.2025/394)

## Abstract

Spatio-temporal data mining is crucial for decision-making and planning in diverse domains. However, in real-world scenarios, training and testing data are often not independent or identically distributed due to rapid changes in data distributions over time and space, resulting in spatio-temporal out-of-distribution (OOD) challenges. This non-stationarity complicates accurate predictions and has motivated research efforts focused on mitigating non-stationarity through normalization operations. Existing methods, nonetheless, often address individual time series in isolation, neglecting correlations across series, which limits their capacity to handle complex spatio-temporal dynamics and results in suboptimal solutions. To overcome these challenges, we propose Clustering Adaptive Normalization (CAN-ST), a general and model-agnostic method that mitigates non-stationarity by capturing both localized distributional changes and shared patterns across nodes via adaptive clustering and a parameter register. As a plugin, CAN-ST can be easily integrated into various spatio-temporal prediction models. Extensive experiments on multiple datasets with diverse forecasting models demonstrate that CAN-ST consistently improves performance by over 20% on average and outperforms state-of-the-art normalization methods.