发表机构
Fudan University; Nanyang Technological University; Zhuhai Fudan Innovation Research Institute; Guangzhou University（复旦大学; 南洋理工大学; 珠海复旦创新研究院; 广州大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对传感器网络覆盖不足导致的未观测节点状态预测难题，提出GenST框架，利用大语言模型提取语义特征作为桥梁，结合时空VAE和生成式Transformer两阶段生成，在零样本预测中显著优于基线。
AI 中文摘要
时空预测是物流、城市规划和智能交通系统的基石。然而，受部署成本和维护资源的限制，传感器网络往往缺乏全面的空间覆盖，使得预测未观测节点状态（FUNS）成为一项关键但艰巨的挑战。传统模型依赖历史观测，在面对没有先前记录的节点时通常会失效。为解决此问题，我们将该问题重新定义为时空图上的条件生成任务，并提出GenST框架，该框架引入大语言模型（LLMs）作为语义桥梁，利用经过微调的预训练LLM从节点描述（如功能区和道路网络结构）中提取丰富的语义特征，以补偿缺失的时空信号。具体而言，我们设计了一个两阶段生成架构：首先，时空变分自编码器（Spatio-Temporal VAE）将时空动态压缩到潜在空间；随后，生成式Transformer（GenT）在包括语义、地理坐标和邻域上下文在内的多模态条件引导下，从噪声中重建未观测节点的未来状态。在六个交通数据集和两个非交通数据集上的实验表明，GenST在零样本预测任务中显著优于现有基线，展示了语义引导生成在缓解时空数据稀疏性方面的实际潜力。
英文摘要
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.
