ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (12) · 13419-13427
DOI: 10.1609/aaai.v39i12.33465 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Qi Zheng und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
Spatial-temporal forecasting is crucial and widely applicable in various domains such as traffic, energy, and climate. Benefiting from the abundance of unlabeled spatial-temporal data, self-supervised methods are increasingly adapted to learn spatial-temporal representations. However, it encounters three key challenges: 1) the difficulty in selecting reliable negative pairs due to the homogeneity of variables, hindering contrastive learning methods; 2) overlooking spatial correlations across variables over time; 3) limitations of efficiency and scalability in existing self-supervised learning methods. To tackle these, we propose a lightweight representation-learning model ST-ReP, integrating current value reconstruction and future value prediction into the pre-training framework for spatial-temporal forecasting. And we design a new spatial-temporal encoder to model fine-grained relationships. Moreover, multi-time scale analysis is incorporated into the self-supervised loss to enhance predictive capability. Experimental results across diverse domains demonstrate that the proposed model surpasses pre-training-based baselines, showcasing its ability to learn compact and semantically enriched representations while exhibiting superior scalability.
Zitieren
APA
Zheng, Q., Yao, Z., & Zhang, Y. (2025). ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 39(12), 13419-13427. https://doi.org/10.1609/aaai.v39i12.33465
Vancouver
Zheng Q, Yao Z, Zhang Y. ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(12):13419-13427. doi:10.1609/aaai.v39i12.33465
BibTeX
@article{Zheng2025,
author = {Zheng, Qi and Yao, Zihao and Zhang, Yaying},
title = {ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {12},
pages = {13419--13427},
doi = {10.1609/aaai.v39i12.33465}
}
EUVIMED