提出时间序列解耦表征框架，无需数据增强也能学出更清晰的特征。
Self-Supervised Learning of Disentangled Representations for Multivariate Time-Series
- 用[CLS]标记分离时间点和样本级特征，实现双层级解耦
- 预测时间戳+对比样本任务，提升表征质量，准确率更高
- 不依赖数据增强，避免偏差，适合标签少的工业医疗场景
医疗与工业领域的多变量时间序列数据信息丰富但维度高、无标签。现有自监督方法虽能学习丰富表征，却难以获得解耦嵌入，且存在变换不变性等归纳偏置问题。为此，我们提出TimeDRL框架，通过双层级解耦嵌入：(i) 利用[CLS]标记策略分离时间戳级与实例级嵌入；(ii) 设计时间戳预测与实例对比任务进行表征学习；(iii) 避免使用数据增强以消除归纳偏置。在预测与分类数据集上的实验表明，TimeDRL优于现有方法，半监督设置下有限标签时也表现良好。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。