Adaptive Time Encoding for Irregular Multivariate Time-Series Classification
Sangho Lee, Kyeongseo Min, Youngdoo Son, Hyungrok Do
Abstract
Time series are often irregularly sampled with uneven time intervals. In multivariate cases, such irregularities may lead to misaligned observations across variables and varying observation counts, making it difficult to extract intrinsic patterns and degrading the classification performance of deep learning models. In this study, we propose an adaptive time encoding approach to address the challenge of irregular sampling in multivariate time-series classification. Our approach generates latent representations at learnable reference points that capture missingness patterns in irregular sequences, enhancing classification performance. We also introduce consistency regularization techniques to incorporate intricate temporal and intervariable information into the learned representations. Extensive experiments demonstrate that our method achieves state-of-the-art performance with high computational efficiency in irregular multivariate time-series classification tasks.
BibTeX
@inproceedings{
lee2025adaptive,
title={Adaptive Time Encoding for Irregular Multivariate Time-Series Classification},
author={Sangho Lee and Kyeongseo Min and Youngdoo Son and Hyungrok Do},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=l0kR6m9NDT}
}