arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.12409cs.LGcs.AI
收藏

用于时间序列表示学习的多源知识混合神经框架

Multi-Source Knowledge-Based Hybrid Neural Framework for Time Series Representation Learning

TCS Research(塔塔咨询服务研究中心)

Sagar Srinivas Sakhinana, Krishna Sai Sudhir Aripirala, Shivam Gupta, Venkataramana Runkana

AI总结:

提出一种混合神经框架,结合领域特定知识与隐式关系结构知识进行多变量时间序列预测,在多个基准上超越现有方法并建模时变不确定性。

摘要:

准确预测复杂动态系统的行为对降低风险至关重要,该系统以互联传感器网络中的高维多变量时间序列(MTS)为特征。尽管图预测网络(GFNs)非常适合预测展现时空依赖性的MTS数据,但先前的工作仅依赖时间序列变量间相互关系的领域特定知识来建模非线性动态,忽略了MTS数据中变量固有的关系结构依赖。相反,当代研究虽从MTS数据推断关系结构,却忽略了领域特定知识。提出的混合架构通过使用基于知识的组合泛化,结合了MTS数据底层关系结构的领域特定知识与隐式知识,从而解决了这些局限。该混合架构在多个基准数据集上展现出优异结果,优于最先进的预测方法。此外,该架构还能对多视界预测的时变不确定性进行建模。

英文摘要:

Accurately predicting the behavior of complex dynamical systems, characterized by high-dimensional multivariate time series(MTS) in interconnected sensor networks, is crucial for informed decision-making in various applications to minimize risk. While graph forecasting networks(GFNs) are ideal for forecasting MTS data that exhibit spatio-temporal dependencies, prior works rely solely on the domain-specific knowledge of time-series variables inter-relationships to model the nonlinear dynamics, neglecting inherent relational structural dependencies among the variables within the MTS data. In contrast, contemporary works infer relational structures from MTS data but neglect domain-specific knowledge. The proposed hybrid architecture addresses these limitations by combining both domain-specific knowledge and implicit knowledge of the relational structure underlying the MTS data using Knowledge-Based Compositional Generalization. The hybrid architecture shows promising results on multiple benchmark datasets, outperforming state-of-the-art forecasting methods. Additionally, the architecture models the time varying uncertainty of multi-horizon forecasts.

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。

↑