arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.37598cs.LGcs.AIcs.NE
收藏

GAS-PFN:用于零样本交通预测的图感知时空先验数据拟合网络

GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting

Kennesaw State University(肯尼索州立大学);Missouri State University(密苏里州立大学)

Joseph Natter, Long Vu, Yifan Zhang, Bobin Deng, Kun Suo, Rui Wu

AI总结:

提出GAS-PFN,将图感知交通建模与零样本适应结合,通过图结构相关设计提升零样本交通预测性能,在6个基准上较同类模型显著降低MSE。

摘要:

交通预测需要建模复杂的时间动态以及道路拓扑结构带来的空间依赖关系。基于图的监督模型表现出色,但通常针对特定数据集和传感器图进行训练,导致部署到新的或不断演变的网络时成本高昂。先验数据拟合网络(PFNs)提供了一种零样本替代方案,通过从合成任务先验中学习上下文推理,合成任务先验提供了编码特定领域假设的显式机制。然而,现有的预测PFN并未显式表示支配交通动态的图结构依赖关系。为了将图感知交通建模与零样本适应相结合,我们提出了图感知时空先验数据拟合网络(GAS-PFN)。GAS-PFN通过随机游走扩散将采样的道路拓扑结构纳入其合成任务先验,使模型在预训练期间学习图耦合动态。其协同设计的推理架构使用两次通过共享Transformer骨干的掩码条件传递,分别建模传感器特定的时间动态和相邻传感器之间的时空交互,之后整合它们的表示进行预测。该设计使GAS-PFN能够在不进行参数更新的情况下利用目标网络结构和上下文。在6个基准的90分钟预测 horizon 下,GAS-PFN相对于其最接近的基于PFN的前身TimePFN,平均降低了34.0%的均方误差(MSE);相对于4个近期行业开发的通用零样本预测器,平均降低了27.7%的MSE。在该比较中,所有模型均接收90分钟的连续近期历史,任何额外上下文均来自每个数据集的时间训练分割。这些结果表明,使PFN的先验和推理架构与图结构对齐可改善零样本交通预测的上下文学习效果。

英文摘要:

Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology. Supervised graph-based models achieve strong performance, but are often trained for a particular dataset and sensor graph, making deployment to new or evolving networks costly. Prior-Data Fitted Networks (PFNs) offer a zero-shot alternative by learning in-context inference from synthetic task priors, which provide an explicit mechanism for encoding domain-specific assumptions. Existing forecasting PFNs, however, do not explicitly represent the graph-structured dependencies governing traffic dynamics. To combine graph-aware traffic modeling with zero-shot adaptation, we introduce the Graph-Aware Spatiotemporal Prior-Data Fitted Network (GAS-PFN). GAS-PFN incorporates sampled road topology into its synthetic task prior through random-walk diffusion, teaching the model to learn graph-coupled dynamics during pretraining. Its co-designed inference architecture uses two mask-conditioned passes through a shared Transformer backbone to separately model sensor-specific temporal dynamics and spatiotemporal interactions among neighboring sensors before integrating their representations for prediction. This design enables GAS-PFN to use target-network structure and context without parameter updates. Across six benchmarks at the 90-minute horizon, GAS-PFN reduces MSE by 34.0% on average relative to TimePFN, its closest PFN-based predecessor. It also reduces MSE by 27.7% on average relative to four recent industry-developed general-purpose zero-shot forecasters. In this comparison, all models receive 90 minutes of contiguous recent history, and any additional context is drawn from each dataset's chronological training split. These results indicate that aligning PFN priors and inference architectures with graph structure improves in-context learning for zero-shot traffic forecasting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑