arXiv：cs.LG· Yue Wang, Djellel Difallah, Areg Karapetyan, Samer Madanat·· 7 小时前AI 评分32
UniST-Pred：面向交通网络中断场景的鲁棒统一时空交通预测框架
UniST-Pred: A Robust Unified Framework for Spatio-Temporal Traffic Forecasting in Transportation Networks Under Disruptions
AI 导读
研究者提出 UniST-Pred 统一时空交通预测框架，先将时间建模与空间表征学习解耦，再通过自适应表征级融合整合两者。团队基于 MATSim 微观交通模拟器构建数据集，在严重网络中断场景下评估该框架，并在标准交通预测数据集上与现有成熟模型对比，验证其轻量设计下仍具竞争力，且能产出可解释的时空表征。源码与数据集已公开。
正文
Abstract:Spatio-temporal traffic forecasting is a core component of intelligent transportation systems, supporting various downstream tasks such as signal control and network-level traffic management. In real-world deployments, forecasting models must operate under structural and observational uncertainties, conditions that are rarely considered in model design. Recent approaches achieve strong short-term predictive performance by tightly coupling spatial and temporal modeling, often at the cost of increased complexity and limited modularity. In contrast, efficient time-series models capture long-range temporal dependencies without relying on explicit network structure. We propose UniST-Pred, a unified spatio-temporal forecasting framework that first decouples temporal modeling from spatial representation learning, then integrates both through adaptive representation-level fusion. To assess robustness of the proposed approach, we construct a dataset based on an agent-based, microscopic traffic simulator (MATSim) and evaluate UniST-Pred under severe network disconnection scenarios. Additionally, we benchmark UniST-Pred on standard traffic prediction datasets, demonstrating its competitive performance against existing well-established models despite a lightweight design. The results illustrate that UniST-Pred maintains strong predictive performance across both real-world and simulated datasets, while also yielding interpretable spatio-temporal representations under infrastructure disruptions. The source code and the generated dataset are available at this https URL
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.14049 [cs.LG] |
| (or arXiv:2602.14049v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2602.14049 arXiv-issued DOI via DataCite |
Submission history
From: Yue Wang [view email]
[v1]
Sun, 15 Feb 2026 08:28:56 UTC (6,841 KB)
[v2]
Wed, 30 Sep 2026 07:31:21 UTC (3,970 KB)
[v3]
Tue, 6 Oct 2026 06:13:04 UTC (3,970 KB)
来源：arXiv：cs.LG · arxiv.org