UltraSTF: Ultra-Compact Model for Large-Scale Spatio-Temporal Forecasting
Year: 2025
Type: preprint
Abstract: Spatio-temporal data, prevalent in real-world applications such as traffic monitoring, financial transactions, and ride-share demands, represents a specialized case of multivariate time series characterized by high dimensionality. This high dimensionality necessitates computationally efficient models and benefits from applying univariate forecasting approaches through channel-independent strategies. SparseTSF, a recently proposed competitive univariate forecasting model, leverages periodicity to achieve compactness by focusing on cross-period dynamics, extending the Pareto frontier in terms of model size and predictive performance. However, it underperforms on spatio-temporal data due to limited capture of intra-period temporal dependencies. To address this limitation, we propose UltraSTF, which integrates a cross-period forecasting component with an ultra-compact shape bank component. Our model efficiently captures recurring patterns in time series using the attention mechanism of the shape bank component, significantly enhancing its capability to learn intra-period dynamics. UltraSTF achieves state-of-the-art performance on the LargeST benchmark while utilizing fewer than 0.2% of the parameters required by the second-best methods, thereby further extending the Pareto frontier of existing approaches.
Source: arXiv (Cornell University)
Authors: Yeh, Chin-Chia Michael, Fan, Xiran, Jiang, Zhimeng, Fan, Yujie, Chen, Huiyuan, Saini, Uday Singh, Lai, Vivian, Dai, Xin, Wang, Junpeng, Zhuang, Zhongfang, Wang, Liang, Zheng, Yan
Language: English
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6891936068
Cites:
Cited by:
Related to: