A Multi-Resolution Multi-Domain Pre-Training Framework for Universal Traffic Forecasting

2026-09-12

AI Summary

为解决交通数据异质性带来的大规模建模难题，提出FlexST框架，通过多分辨率时空扩散模块和域自适应专家混合模型来提高模型的泛化能力和效率。

Abstract

Spatio-temporal traffic data are central to intelligent transportation systems, yet their heterogeneity poses significant challenges for large-scale modeling. Existing pre-trained models often rely on a homogeneous modeling paradigm to handle highly heterogeneous traffic data. This fundamental mismatch not only limits model generalization but also leads to computationally expensive and parameter-inefficient designs. To this end, we propose FlexST, a novel pre-training framework that introduces modularity and adaptivity for traffic modeling. Specifically, we first propose a multi-resolution spatio-temporal diffusion module that captures both short-term fluctuations and long-range trends, effectively reconciling inputs with divergent temporal and spatial resolutions. After that, we construct a domain-adaptive mixture-of-experts that dynamically routes data to specialized sub-networks, enabling selective knowledge transfer while preventing negative interference across diverse domains. Moreover, we devise a unified periodic encoding strategy that injects resolution- and domain-aware inductive biases to harmonize periodic inconsistencies across datasets. Extensive experiments on 23 real-world traffic datasets demonstrate that FlexST significantly outperforms state-of-the-art baselines in zero- and few-shot settings, showcasing superior generalization, adaptability and efficiency. This work offers a new direction for building general-purpose pre-trained models capable of handling the complexity and variability of urban traffic systems.

Problem

• spatio-temporal traffic data
• heterogeneity
• large-scale modeling
• pre-trained models
• generalization

Innovation

• multi-resolution spatio-temporal diffusion
• domain-adaptive mixture-of-experts
• unified periodic encoding