Spatio-temporal Multivariate Time Series Forecast with Chosen Variables

2025-10-27

AI Summary

This paper addresses the long-overlooked yet critical problem of sensor variable selection in spatiotemporal multivariate time series forecasting. Unlike existing methods that assume fixed input variables, we propose the first unified framework that jointly optimizes variable selection and model performance. Given *n* candidate monitoring locations, our approach dynamically selects the *m* most predictive variables—crucial for resource-constrained sensor deployment. Key innovations include: (i) mask-driven joint pruning of variables and model parameters; (ii) magnitude-aware attention pruning; (iii) priority-based sample replay; (iv) learnable spatial embeddings; and (v) adjacency-aware information propagation. These components synergistically enhance both accuracy and efficiency. Extensive experiments on five real-world datasets demonstrate consistent superiority over state-of-the-art baselines: average prediction error decreases by 12.6%, while inference speed improves by 1.8×.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Time-Series/Data Streams
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

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.

Problem

• Optimally selecting m-out-of-n variables for STMF input
• Jointly performing variable selection and model optimization
• Maximizing forecast accuracy with constrained sensor deployment

Innovation

• Jointly optimizes variable selection and model parameters
• Uses quantile-based masking to prune less informative variables
• Propagates information via learnable embeddings and adjacency