Spatio-temporal Multivariate Time Series Forecast with Chosen Variables

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Zibo, Jiang, Zhe, Xu, Zelin, Xiao, Tingsong, Zhang, Yupu, Xiao, Zhengkun, Wang, Haibo, Chen, Shigang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918175167217664
author Liu, Zibo
Jiang, Zhe
Xu, Zelin
Xiao, Tingsong
Zhang, Yupu
Xiao, Zhengkun
Wang, Haibo
Chen, Shigang
author_facet Liu, Zibo
Jiang, Zhe
Xu, Zelin
Xiao, Tingsong
Zhang, Yupu
Xiao, Zhengkun
Wang, Haibo
Chen, Shigang
contents Spatio-Temporal Multivariate time series Forecast (STMF) uses the time series of $n$ spatially distributed variables in a period of recent past to forecast their values in a period of near future. It has important applications in spatio-temporal sensing forecast such as road traffic prediction and air pollution prediction. Recent papers have addressed a practical problem of missing variables in the model input, which arises in the sensing applications where the number $m$ of sensors is far less than the number $n$ of locations to be monitored, due to budget constraints. We observe that the state of the art assumes that the $m$ variables (i.e., locations with sensors) in the model input are pre-determined and the important problem of how to choose the $m$ variables in the input has never been studied. This paper fills the gap by studying a new problem of STMF with chosen variables, which optimally selects $m$-out-of-$n$ variables for the model input in order to maximize the forecast accuracy. We propose a unified framework that jointly performs variable selection and model optimization for both forecast accuracy and model efficiency. It consists of three novel technical components: (1) masked variable-parameter pruning, which progressively prunes less informative variables and attention parameters through quantile-based masking; (2) prioritized variable-parameter replay, which replays low-loss past samples to preserve learned knowledge for model stability; (3) dynamic extrapolation mechanism, which propagates information from variables selected for the input to all other variables via learnable spatial embeddings and adjacency information. Experiments on five real-world datasets show that our work significantly outperforms the state-of-the-art baselines in both accuracy and efficiency, demonstrating the effectiveness of joint variable selection and model optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24027
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spatio-temporal Multivariate Time Series Forecast with Chosen Variables
Liu, Zibo
Jiang, Zhe
Xu, Zelin
Xiao, Tingsong
Zhang, Yupu
Xiao, Zhengkun
Wang, Haibo
Chen, Shigang
Machine Learning
Artificial Intelligence
Spatio-Temporal Multivariate time series Forecast (STMF) uses the time series of $n$ spatially distributed variables in a period of recent past to forecast their values in a period of near future. It has important applications in spatio-temporal sensing forecast such as road traffic prediction and air pollution prediction. Recent papers have addressed a practical problem of missing variables in the model input, which arises in the sensing applications where the number $m$ of sensors is far less than the number $n$ of locations to be monitored, due to budget constraints. We observe that the state of the art assumes that the $m$ variables (i.e., locations with sensors) in the model input are pre-determined and the important problem of how to choose the $m$ variables in the input has never been studied. This paper fills the gap by studying a new problem of STMF with chosen variables, which optimally selects $m$-out-of-$n$ variables for the model input in order to maximize the forecast accuracy. We propose a unified framework that jointly performs variable selection and model optimization for both forecast accuracy and model efficiency. It consists of three novel technical components: (1) masked variable-parameter pruning, which progressively prunes less informative variables and attention parameters through quantile-based masking; (2) prioritized variable-parameter replay, which replays low-loss past samples to preserve learned knowledge for model stability; (3) dynamic extrapolation mechanism, which propagates information from variables selected for the input to all other variables via learnable spatial embeddings and adjacency information. Experiments on five real-world datasets show that our work significantly outperforms the state-of-the-art baselines in both accuracy and efficiency, demonstrating the effectiveness of joint variable selection and model optimization.
title Spatio-temporal Multivariate Time Series Forecast with Chosen Variables
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.24027