arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.00725cs.LG
收藏

理解与缓解路径数据扩散中的高计算成本

Understanding and Mitigating the High Computational Cost in Path Data Diffusion

Beihang University(北京航空航天大学)

Dingyuan Shi, Lulu Zhang, Yongxin Tong, Ke Xu

AI总结:

本文分析了图空间扩散过程在路径生成中的高计算成本问题,提出潜在空间路径扩散(LPD)模型,在保持性能的同时显著降低时间和内存成本,并在多数场景下超越现有方法。

摘要:

移动服务、导航系统和智能交通技术的进步使得收集大量路径数据成为可能。对这种路径数据的分布进行建模,被称为路径生成(PG)问题,对于理解城市出行模式和开发智能交通系统至关重要。最近的研究探索了使用扩散模型来解决PG问题,因为它们能够捕获多模态分布并支持条件生成。最近的一项工作在图空间中显式设计了扩散过程,并实现了最先进的性能。然而,这种方法在时间和内存方面都存在很高的计算成本,这限制了其应用。在本文中,我们从理论和实验两方面分析了这种方法,发现其高计算成本的主要原因是其在图空间中显式设计扩散过程。为了提高效率,我们设计了一种潜在空间路径扩散(LPD)模型,它在潜在空间而不是图空间中运行。我们的LPD分别将时间和内存成本最多降低了82.8%和83.1%。尽管有这些降低,我们的方法并没有出现性能下降。它在大多数场景下比最先进的方法高出24.5%~34.0%。

英文摘要:

Advancements in mobility services, navigation systems, and smart transportation technologies have made it possible to collect large amounts of path data. Modeling the distribution of this path data, known as the Path Generation (PG) problem, is crucial for understanding urban mobility patterns and developing intelligent transportation systems. Recent studies have explored using diffusion models to address the PG problem due to their ability to capture multimodal distributions and support conditional generation. A recent work devises a diffusion process explicitly in graph space and achieves state-of-the-art performance. However, this method suffers a high computation cost in terms of both time and memory, which prohibits its application. In this paper, we analyze this method both theoretically and experimentally and find that the main culprit of its high computation cost is its explicit design of the diffusion process in graph space. To improve efficiency, we devise a Latent-space Path Diffusion (LPD) model, which operates in latent space instead of graph space. Our LPD significantly reduces both time and memory costs by up to 82.8% and 83.1%, respectively. Despite these reductions, our approach does not suffer from performance degradation. It outperforms the state-of-the-art method in most scenarios by 24.5%~34.0%.

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。

↑