TY - JOUR
T1 - Spatio-Temporal Consistency for Multivariate Time-Series Representation Learning
AU - Lee, Sangho
AU - Kim, Wonjoon
AU - Son, Youngdoo
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2024
Y1 - 2024
N2 - Label sparsity in multivariate time series (MTS) makes using label information for practical applications challenging. Thus, unsupervised representation learning methods have gained attention to learn effective representations suitable for various MTS tasks without relying on labels. Recently, contrastive learning has emerged as a promising approach to generate robust representations by capturing underlying MTS information. However, the existing methods have some limitations, such as insufficient consideration of cross-variable relationships of MTS and high sensitivity to positive pairs. Therefore, we proposed a novel spatio-temporal contrastive representation learning method (STCR) designed to address these limitations. STCR focuses on learning robust representations by encouraging spatio-temporal consistency, which comprehensively considers spatial information as well as temporal dependencies in MTS. The results of extensive experiments on MTS classification and forecasting tasks demonstrate the efficacy of STCR in generating high-quality representations, achieving state-of-the-art performance on both tasks.
AB - Label sparsity in multivariate time series (MTS) makes using label information for practical applications challenging. Thus, unsupervised representation learning methods have gained attention to learn effective representations suitable for various MTS tasks without relying on labels. Recently, contrastive learning has emerged as a promising approach to generate robust representations by capturing underlying MTS information. However, the existing methods have some limitations, such as insufficient consideration of cross-variable relationships of MTS and high sensitivity to positive pairs. Therefore, we proposed a novel spatio-temporal contrastive representation learning method (STCR) designed to address these limitations. STCR focuses on learning robust representations by encouraging spatio-temporal consistency, which comprehensively considers spatial information as well as temporal dependencies in MTS. The results of extensive experiments on MTS classification and forecasting tasks demonstrate the efficacy of STCR in generating high-quality representations, achieving state-of-the-art performance on both tasks.
KW - Contrastive learning
KW - cross-variable relations
KW - multivariate time series
KW - representation learning
KW - temporal dependency
UR - http://www.scopus.com/inward/record.url?scp=85186959015&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2024.3369679
DO - 10.1109/ACCESS.2024.3369679
M3 - Article
AN - SCOPUS:85186959015
SN - 2169-3536
VL - 12
SP - 30962
EP - 30975
JO - IEEE Access
JF - IEEE Access
ER -