Multivariate time-series data in fields like healthcare and industry are informative but challenging due to high dimensionality and lack of labels. Recent self-supervised learning methods excel in learning rich representations without labels but struggle with disentangled embeddings and inductive bias issues like transformation-invariance. To address these challenges, we introduce TimeDRL, a framework for multivariate time-series representation learning with dual-level disentangled embeddings. TimeDRL features: (i) disentangled timestamp-level and instance-level embeddings using a [CLS] token strategy; (ii) timestamp-predictive and instance-contrastive tasks for representation learning; and (iii) avoidance of augmentation methods to eliminate inductive biases. Experiments on forecasting and classification datasets show TimeDRL outperforms existing methods, with further validation in semi-supervised settings with limited labeled data.
@article{arxiv.2410.12606,
title = {Self-Supervised Learning of Disentangled Representations for Multivariate Time-Series},
author = {Ching Chang and Chiao-Tung Chan and Wei-Yao Wang and Wen-Chih Peng and Tien-Fu Chen},
journal= {arXiv preprint arXiv:2410.12606},
year = {2024}
}
Comments
This submission has been withdrawn to avoid duplication with a full version of the paper that is already available in another arXiv entry (arXiv:2410.12606). The withdrawn version was a short format prepared for a NeurIPS workshop and is no longer necessary as a separate arXiv submission