通过自注意和相对位置注入增强多变量时间序列分类器
Enhancing Multivariate Time Series Classifiers through Self-Attention and Relative Positioning Infusion
摘要:
时间序列分类(TSC)是许多视觉计算应用中的一个重要且具有挑战性的任务。尽管为TSC开发了广泛的方法,但相对较少使用深度神经网络(DNN)。在本文中,我们提出了两个新的注意力块(全局时间注意力和时间伪高斯增强自注意力),可以增强基于深度学习的TSC方法,即使这些方法是针对特定数据集或任务设计和优化的。我们通过在东安格利亚大学(UEA)基准测试中评估多个最先进的基于深度学习的TSC模型来验证这一说法,该基准测试是30个多变量时间序列分类(MTSC)数据集的标准化集合。我们发现,添加建议的注意力块可以将基础模型的平均准确度提高3.6%。此外,建议的TPS块使用一个新的注入模块,包括Transformers中的相对位置信息。作为一个具有较低计算复杂性的独立单元,它使TPS能够比大多数最先进的基于DNN的TSC方法执行得更好。我们的实验设置和建议的注意力块的源代码是公开的。
英文摘要:
Time Series Classification (TSC) is an important and challenging task for many visual computing applications. Despite the extensive range of methods developed for TSC, relatively few utilized Deep Neural Networks (DNNs). In this paper, we propose two novel attention blocks (Global Temporal Attention and Temporal Pseudo-Gaussian augmented Self-Attention) that can enhance deep learning-based TSC approaches, even when such approaches are designed and optimized for a specific dataset or task. We validate this claim by evaluating multiple state-of-the-art deep learning-based TSC models on the University of East Anglia (UEA) benchmark, a standardized collection of 30 Multivariate Time Series Classification (MTSC) datasets. We show that adding the proposed attention blocks improves base models' average accuracy by up to 3.6%. Additionally, the proposed TPS block uses a new injection module to include the relative positional information in transformers. As a standalone unit with less computational complexity, it enables TPS to perform better than most of the state-of-the-art DNN-based TSC methods. The source codes for our experimental setups and proposed attention blocks are made publicly available.
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。