Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zheng, Qi, Yao, Zihao, Zhang, Yaying
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.14537
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912161258799104
author Zheng, Qi
Yao, Zihao
Zhang, Yaying
author_facet Zheng, Qi
Yao, Zihao
Zhang, Yaying
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14537
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting
Zheng, Qi
Yao, Zihao
Zhang, Yaying
Machine Learning
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.
title ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting
topic Machine Learning
url https://arxiv.org/abs/2412.14537