Understanding and Mitigating the High Computational Cost in Path Data Diffusion
This work addresses efficiency issues for researchers and practitioners in mobility and transportation systems, offering a more scalable solution for path data modeling.
The paper tackles the high computational cost of a state-of-the-art diffusion model for path generation by analyzing its inefficiencies and proposing a latent-space approach, reducing time and memory costs by up to 82.8% and 83.1% while improving performance by 24.5%~34.0% in most scenarios.
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%.