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 2109.01657cs.LG
收藏

多变量时间序列预测的多视图多任务学习框架

A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting

Australian Artificial Intelligence Institute, University of Technology Sydney(悉尼科技大学澳大利亚人工智能研究院);Southern University of Science and Technology(南方科技大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);Center for Spatial Information Science, University of Tokyo(东京大学空间信息科学中心)

Jinliang Deng, Xiusi Chen, Renhe Jiang, Xuan Song, Ivor W. Tsang

摘要:

多变量时间序列(MTS)数据是现实世界中普遍存在的一类数据抽象。MTS的任何实例都是从一个混合动力系统中产生的,它们的具体动力学通常是未知的。这种动态系统的混合性质是复杂的外部属性的结果,例如地理位置和一天中的时间,其中的每一个可以被分类为空间属性或时间属性。因此,有两个基本的视图,可以用来分析MTS数据,即空间视图和时间视图。此外,从这两个视图中的每一个,我们可以划分MTS的数据样本集不相交的预测任务,根据其相关的属性值。然后,相同任务的样本将表现出类似的即将到来的模式,这是不太复杂的预测相比,原始的单视图设置。考虑到这一点,我们提出了一种新的多视图多任务(MVMT)学习框架MTS预测。在大多数场景中,MVMT信息并没有被显式地呈现,而是深深地隐藏在MTS数据中,这严重阻碍了模型自然地捕获它。为此,我们开发了两种基本的操作,即任务明智的仿射变换和任务明智的归一化,分别。在空间和时间视图上应用这两个具有先验知识的操作允许模型在预测时自适应地提取MVMT信息。在三个数据集上进行了大量的实验,以说明规范架构可以大大提高MVMT学习框架的有效性和效率。此外,我们设计了丰富的案例研究,以揭示在整个预测过程中的不同阶段产生的表示的属性。

英文摘要:

Multi-variate time series (MTS) data is a ubiquitous class of data abstraction in the real world. Any instance of MTS is generated from a hybrid dynamical system and their specific dynamics are usually unknown. The hybrid nature of such a dynamical system is a result of complex external attributes, such as geographic location and time of day, each of which can be categorized into either spatial attributes or temporal attributes. Therefore, there are two fundamental views which can be used to analyze MTS data, namely the spatial view and the temporal view. Moreover, from each of these two views, we can partition the set of data samples of MTS into disjoint forecasting tasks in accordance with their associated attribute values. Then, samples of the same task will manifest similar forthcoming pattern, which is less sophisticated to be predicted in comparison with the original single-view setting. Considering this insight, we propose a novel multi-view multi-task (MVMT) learning framework for MTS forecasting. Instead of being explicitly presented in most scenarios, MVMT information is deeply concealed in the MTS data, which severely hinders the model from capturing it naturally. To this end, we develop two kinds of basic operations, namely task-wise affine transformation and task-wise normalization, respectively. Applying these two operations with prior knowledge on the spatial and temporal view allows the model to adaptively extract MVMT information while predicting. Extensive experiments on three datasets are conducted to illustrate that canonical architectures can be greatly enhanced by the MVMT learning framework in terms of both effectiveness and efficiency. In addition, we design rich case studies to reveal the properties of representations produced at different phases in the entire prediction procedure.

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。

↑