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 2408.06672cs.LGcs.AI
收藏

TimeBridge: 通过桥模型改进扩散先验设计以实现时间序列生成

TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generation

Korea Institute for Advanced Study(韩国高级研究院);Seoul National University(首尔国立大学)

Jinseong Park, Seungyun Lee, Woojin Jeong, Yujin Choi, Jaewook Lee

AI总结:

TimeBridge通过桥模型改进扩散先验设计,提升时间序列生成的灵活性和性能。

摘要:

时间序列生成在现实世界应用中被广泛使用,如模拟、数据增强和假设检验。最近,扩散模型已成为时间序列生成的主流方法,能够实现多样化的合成场景。然而,固定的标准高斯扩散先验可能不适合时间序列数据,这些数据具有时间顺序和固定时间点的特性。在本文中,我们提出了TimeBridge框架,通过使用扩散桥来学习从所选先验到数据分布之间的路径,灵活地合成时间序列数据。我们随后探索了几种针对时间序列合成设计的先验方案。我们的框架涵盖(i)用于无条件生成的数据和时间依赖先验,以及(ii)用于条件生成的尺度保持先验。实验表明,我们的框架结合数据驱动的先验在时间序列生成任务中优于标准扩散模型。

英文摘要:

Time series generation is widely used in real-world applications such as simulation, data augmentation, and hypothesis testing. Recently, diffusion models have emerged as the de facto approach to time series generation, enabling diverse synthesis scenarios. However, the fixed standard-Gaussian diffusion prior may be ill-suited for time series data, which exhibit properties such as temporal order and fixed time points. In this paper, we propose TimeBridge, a framework that flexibly synthesizes time series data by using diffusion bridges to learn paths between a chosen prior and the data distribution. We then explore several prior designs tailored to time series synthesis. Our framework covers (i) data- and time-dependent priors for unconditional generation and (ii) scale-preserving priors for conditional generation. Experiments show that our framework with data-driven priors outperforms standard diffusion models on time series generation.

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。

↑