SVP-T: A Shape-level Variable-Position Transformer for Multivariate Time Series Classification

Rundong Zuo*, Guozhong Li, Byron Choi, Sourav S. Bhowmick, Daphne Ngar Yin Mah, Grace Lai Hung Wong

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review


Multivariate time series classification (MTSC), one of the most fundamental time series applications, has not only gained substantial research attentions but has also emerged in many real-life applications. Recently, using transformers to solve MTSC has been reported. However, current transformer-based methods take data points of individual timestamps as inputs (timestamp-level), which only capture the temporal dependencies, not the dependencies among variables. In this paper, we propose a novel method, called SVP-T. Specifically, we first propose to take time series subsequences, which can be from different variables and positions (time interval), as the inputs (shape-level). The temporal and variable dependencies are both handled by capturing the long- and short-term dependencies among shapes. Second, we propose a variable-position encoding layer (VP-layer) to utilize both the variable and position information of each shape. Third, we introduce a novel VP-based (Variable-Position) self-attention mechanism to allow the enhancing of the attention weights of overlapping shapes. We evaluate our method on all UEA MTS datasets. SVP-T achieves the best accuracy rank compared with several competitive state-of-the-art methods. Furthermore, we demonstrate the effectiveness of the VP-layer and the VP-based self-attention mechanism. Finally, we present one case study to interpret the result of SVP-T.
Original languageEnglish
Title of host publicationProceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
EditorsBrian Williams, Yiling Chen, Jennifer Neville
Place of PublicationWashington, DC
PublisherAAAI press
Number of pages9
ISBN (Electronic)9781577358800
Publication statusPublished - 27 Jun 2023
Event37th AAAI Conference on Artificial Intelligence, AAAI 2023 - Washington, United States
Duration: 7 Feb 202314 Feb 2023

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468


Conference37th AAAI Conference on Artificial Intelligence, AAAI 2023
Country/TerritoryUnited States
Internet address

User-Defined Keywords

  • ML: Time-Series/Data Streams
  • DMKM: Mining of Spatial
  • Temporal or Spatio-Temporal Data


Dive into the research topics of 'SVP-T: A Shape-level Variable-Position Transformer for Multivariate Time Series Classification'. Together they form a unique fingerprint.

Cite this