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 2103.14438cs.LG
收藏

用于多变量时间序列分类的门控Transformer网络

Gated Transformer Networks for Multivariate Time Series Classification

Zhengzhou University(郑州大学);Statistical information center of Henan health commission(河南省卫生健康委员会统计信息中心);Facebook AI(脸书人工智能研究院)

Minghao Liu, Shengqi Ren, Siyuan Ma, Jiahui Jiao, Yizhou Chen, Zhiguang Wang, Wei Song

摘要:

用于时间序列分类的深度学习模型(主要是卷积网络和LSTM)已被社区广泛研究,并在医疗保健,金融,工业工程和物联网等不同领域得到广泛应用。与此同时,Transformer Networks最近在各种自然语言处理和计算机视觉任务上取得了前沿性能。在这项工作中,我们探索了一个简单的扩展,目前的Transformer网络与门控,命名为门控Transformer网络(GTN)的多变量时间序列分类问题。通过合并Transformer的两个塔的门控,它们分别对通道和逐步相关性进行建模,我们展示了GTN如何自然有效地适用于多变量时间序列分类任务。我们对13个数据集进行了全面的实验,并进行了全面的消融研究。我们的研究结果表明,GTN能够实现与当前最先进的深度学习模型竞争的结果。我们还探讨了注意力地图的自然解释GTN的时间序列建模。我们的初步研究结果为Transformer网络在多变量时间序列分类任务上提供了一个强有力的基线,并为未来的研究奠定了基础。

英文摘要:

Deep learning model (primarily convolutional networks and LSTM) for time series classification has been studied broadly by the community with the wide applications in different domains like healthcare, finance, industrial engineering and IoT. Meanwhile, Transformer Networks recently achieved frontier performance on various natural language processing and computer vision tasks. In this work, we explored a simple extension of the current Transformer Networks with gating, named Gated Transformer Networks (GTN) for the multivariate time series classification problem. With the gating that merges two towers of Transformer which model the channel-wise and step-wise correlations respectively, we show how GTN is naturally and effectively suitable for the multivariate time series classification task. We conduct comprehensive experiments on thirteen dataset with full ablation study. Our results show that GTN is able to achieve competing results with current state-of-the-art deep learning models. We also explored the attention map for the natural interpretability of GTN on time series modeling. Our preliminary results provide a strong baseline for the Transformer Networks on multivariate time series classification task and grounds the foundation for future research.

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。

↑