联合模拟用户移动轨迹与手机流量，提升真实感与跨模态关联性。
Multi-Scale Diffusion Transformer for Jointly Simulating User Mobility and Mobile Traffic Pattern
- 基于多尺度分解与混合去噪网络，同步建模连续流量与离散位置序列。
- 在关键统计指标上，流量生成JSD降低17.38%，轨迹生成平均降低39.53%。
- 适合城市规划、网络优化等需高真实度移动行为模拟的场景。
用户移动轨迹和手机流量数据对城市规划、网络优化和应急响应等应用至关重要。然而，由于隐私顾虑和采集成本，大规模细粒度移动数据难以获取，因此生成真实可靠的移动与流量模式尤为关键。用户轨迹与移动流量本质上相互耦合，反映了城市环境中物理移动与数字行为的双重特征。尽管二者存在强依赖关系，现有研究多将其分开建模，限制了跨模态动态的捕捉能力。为此，本文提出MSTDiff：一种用于联合生成手机流量与用户轨迹的多尺度扩散变压器。首先，采用离散小波变换实现流量的多分辨率分解；其次，设计混合去噪网络处理连续流量值与离散位置序列；再通过基于城市知识图谱嵌入相似性的转移机制，引导语义驱动的轨迹生成；最后，引入具备跨注意力机制的多尺度Transformer，捕捉轨迹与流量间的依赖关系。实验表明，MSTDiff在流量与轨迹生成任务中均优于现有最佳基线，流量生成的詹森-香农散度（JSD）最高降低17.38%，轨迹生成平均降低39.53%。代码已开源：https://github.com/tsinghua-fib-lab/MSTDiff。
原文摘要 · Abstract (English)
User mobility trajectory and mobile traffic data are essential for a wide spectrum of applications including urban planning, network optimization, and emergency management. However, large-scale and fine-grained mobility data remains difficult to obtain due to privacy concerns and collection costs, making it essential to simulate realistic mobility and traffic patterns. User trajectories and mobile traffic are fundamentally coupled, reflecting both physical mobility and cyber behavior in urban environments. Despite this strong interdependence, existing studies often model them separately, limiting the ability to capture cross-modal dynamics. Therefore, a unified framework is crucial. In this paper, we propose MSTDiff, a Multi-Scale Diffusion Transformer for joint simulation of mobile traffic and user trajectories. First, MSTDiff applies discrete wavelet transforms for multi-resolution traffic decomposition. Second, it uses a hybrid denoising network to process continuous traffic volumes and discrete location sequences. A transition mechanism based on urban knowledge graph embedding similarity is designed to guide semantically informed trajectory generation. Finally, a multi-scale Transformer with cross-attention captures dependencies between trajectories and traffic. Experiments show that MSTDiff surpasses state-of-the-art baselines in traffic and trajectory generation tasks, reducing Jensen-Shannon divergence (JSD) across key statistical metrics by up to 17.38% for traffic generation, and by an average of 39.53% for trajectory generation. The source code is available at: https://github.com/tsinghua-fib-lab/MSTDiff .
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。