arXiv：cs.CL· Shuhao Li, Weidong Yang, Changan Liu, Wei Zhuo, Yingbo Zhou, Fan Zhang, Siqiang Luo·· 3 小时前AI 评分30
GenST：用 LLM 语义引导生成时空图节点状态，解决未观测节点预测难题
Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States
AI 导读
针对传感器网络空间覆盖不足导致的未观测节点状态预测（FUNS）难题，研究者提出 GenST 框架，将问题重新定义为时空图上的条件生成任务，用预训练 LLM 微调后从节点描述中提取语义特征以补偿缺失的时空信号。
正文
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.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (stat.ML) |
| Cite as: | arXiv:2610.08818 [cs.LG] |
| (or arXiv:2610.08818v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08818 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shuhao Li [view email]
[v1]
Thu, 24 Sep 2026 04:38:54 UTC (1,148 KB)
来源：arXiv：cs.CL · arxiv.org