arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.02682cs.LGeess.SP
收藏

Time Weaver:一种条件时间序列生成模型

Time Weaver: A Conditional Time Series Generation Model

Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, USA(电子与计算机工程系,德克萨斯大学奥斯汀分校,奥斯汀,美国)

Sai Shankar Narasimhan, Shubhankar Agarwal, Oguzhan Akcin, Sujay Sanghavi, Sandeep Chinchali

AI总结:

针对现有时间序列生成方法忽略异构元数据、评估指标存在缺陷的问题,该研究提出基于扩散的TIME WEAVER模型,利用多类型元数据提升生成效果,并设计新评估指标,在多类真实数据集上性能超越SOTA基准最高达30%。

摘要:

设想一下,我们可以基于天气、电动汽车的存在情况以及地理位置生成某城市的电力需求模式,这可用于冬季寒潮期间的容量规划。这类现实世界的时间序列往往配有成对的异构上下文元数据(例如天气和位置信息)。当前的时间序列生成方法通常会忽略这类成对元数据。此外,元数据的异构性给将图像、音频和视频领域现有的条件生成方法适配到时间序列领域带来了若干实际挑战。为填补这一空白,我们提出了TIME WEAVER,这是一种新型的基于扩散的模型,它利用类别型、连续型甚至时变型等形式的异构元数据,显著提升时间序列生成效果。此外,我们发现将图像领域的标准评估指标直接简单扩展到时间序列领域是远远不够的。这些指标不会惩罚那些在生成的时间序列中复现元数据特定特征时特异性较差的条件生成方法。因此,我们创新设计了一种新型评估指标,能够准确衡量条件生成的特异性以及生成时间序列的真实感。我们的实验表明,在现实世界的能源、医疗、空气质量和交通数据集上的下游分类任务中,TIME WEAVER的表现优于生成对抗网络(GANs)等当前最先进的基准模型,性能提升幅度最高可达30%。

英文摘要:

Imagine generating a city's electricity demand pattern based on weather, the presence of an electric vehicle, and location, which could be used for capacity planning during a winter freeze. Such real-world time series are often enriched with paired heterogeneous contextual metadata (e.g., weather and location). Current approaches to time series generation often ignore this paired metadata. Additionally, the heterogeneity in metadata poses several practical challenges in adapting existing conditional generation approaches from the image, audio, and video domains to the time series domain. To address this gap, we introduce TIME WEAVER, a novel diffusion-based model that leverages the heterogeneous metadata in the form of categorical, continuous, and even time-variant variables to significantly improve time series generation. Additionally, we show that naive extensions of standard evaluation metrics from the image to the time series domain are insufficient. These metrics do not penalize conditional generation approaches for their poor specificity in reproducing the metadata-specific features in the generated time series. Thus, we innovate a novel evaluation metric that accurately captures the specificity of conditional generation and the realism of the generated time series. We show that TIME WEAVER outperforms state-of-the-art benchmarks, such as Generative Adversarial Networks (GANs), by up to 30% in downstream classification tasks on real-world energy, medical, air quality, and traffic datasets.

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。

↑