Abstract
Spatio-temporal forecasting is a cornerstone of logistics, urban planning, and intelligent transportation systems. However, constrained by deployment costs and maintenance resources, sensor networks often lack comprehensive spatial coverage, rendering Forecast Unobserved Node States (FUNS) a critical yet formidable challenge. Conventional models rely on historical observations and typically falter when encountering nodes without prior records. To address this, we redefine the problem as a conditional generation task on spatio-temporal graphs and propose GenST, a framework that introduces Large Language Models (LLMs) as a semantic bridge, leveraging a pre-trained LLM fine-tuned to extract rich semantic features from node descriptions, such as functional zones and road network structures, to compensate for missing spatio-temporal signals. Specifically, we design a two-stage generative architecture: a Spatio-Temporal VAE first compresses spatio-temporal dynamics into a latent space, followed by a Generative Transformer (GenT) that reconstructs the future states of unobserved nodes from noise, guided by multi-modal conditions including semantics, geographic coordinates, and neighborhood contexts. Experiments on six traffic and two non-traffic datasets show GenST significantly outperforms existing baselines in zero-shot prediction tasks, demonstrating the practical potential of semantic-guided generation for mitigating spatio-temporal data sparsity.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Li, S., Yang, W., Liu, C., Zhuo, W., Zhou, Y., Zhang, F., & Luo, S. (2026). Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States. https://omanscience.com/en/articles/just-for-funs-llm-guided-spatio-temporal-graph-node-generation-for-forecasting-unobserved-node-states
MLA 9
Li, Shuhao, et al. "Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States." https://omanscience.com/en/articles/just-for-funs-llm-guided-spatio-temporal-graph-node-generation-for-forecasting-unobserved-node-states.
Chicago (author–date)
Li, Shuhao, Weidong Yang, Changan Liu, Wei Zhuo, Yingbo Zhou, Fan Zhang, and Siqiang Luo. 2026. "Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States." https://omanscience.com/en/articles/just-for-funs-llm-guided-spatio-temporal-graph-node-generation-for-forecasting-unobserved-node-states.
Harvard
Li, S., Yang, W., Liu, C., Zhuo, W., Zhou, Y., Zhang, F. and Luo, S. (2026) 'Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States', Available at: https://omanscience.com/en/articles/just-for-funs-llm-guided-spatio-temporal-graph-node-generation-for-forecasting-unobserved-node-states.
Vancouver
Li S, Yang W, Liu C, Zhuo W, Zhou Y, Zhang F, et al. Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States. https://omanscience.com/en/articles/just-for-funs-llm-guided-spatio-temporal-graph-node-generation-for-forecasting-unobserved-node-states
IEEE
S. Li, W. Yang, C. Liu, W. Zhuo, Y. Zhou, F. Zhang, and S. Luo, "Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States," https://omanscience.com/en/articles/just-for-funs-llm-guided-spatio-temporal-graph-node-generation-for-forecasting-unobserved-node-states.