用预训练概率变换器，让城市交通预测更准且能评估不确定性。
A Pretrained Probabilistic Transformer for City-Scale Traffic Volume Prediction
- 把交通流量建模为轨迹分布，融合实时数据与路网结构。
- 在极端数据稀疏时仍优于现有方法，尤其在跨城市场景表现强。
- 适合需要可靠预测置信度的智慧交通系统开发者。
城市级交通流量预测在智能交通系统中至关重要，但受观测数据不完备和偏差影响，仍具挑战性。尽管深度学习方法已展现出潜力，但多数模型仅输出确定性点估计，忽略未观测交通流带来的不确定性。此外，现有模型多为城市特定训练，泛化能力差，难以跨城市扩展。为此，我们提出TrafficPPT——一种预训练的概率变换器，将交通流量建模为轨迹的分布聚合。该框架融合实时观测、历史轨迹数据与路网拓扑，实现鲁棒且具备不确定性感知的交通推断。TrafficPPT首先在大规模模拟数据（覆盖多种城市场景）上预训练，再在目标城市微调以实现有效领域适应。真实数据集实验表明，TrafficPPT持续超越当前最优基线，尤其在数据极度稀疏条件下表现优异。代码将开源。
原文摘要 · Abstract (English)
City-scale traffic volume prediction plays a pivotal role in intelligent transportation systems, yet remains a challenge due to the inherent incompleteness and bias in observational data. Although deep learning-based methods have shown considerable promise, most existing approaches produce deterministic point estimates, thereby neglecting the uncertainty arising from unobserved traffic flows. Furthermore, current models are typically trained in a city-specific manner, which hinders their generalizability and limits scalability across diverse urban contexts. To overcome these limitations, we introduce TrafficPPT, a Pretrained Probabilistic Transformer designed to model traffic volume as a distributional aggregation of trajectories. Our framework fuses heterogeneous data sources-including real-time observations, historical trajectory data, and road network topology-enabling robust and uncertainty-aware traffic inference. TrafficPPT is initially pretrained on large-scale simulated data spanning multiple urban scenarios, and later fine-tuned on target cities to ensure effective domain adaptation. Experiments on real-world datasets show that TrafficPPT consistently surpasses state-of-the-art baselines, particularly under conditions of extreme data sparsity. Code will be open.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。