通过双重掩码重建学习多变量时间序列的无监督表示。
MTS-DMAE: Dual-Masked Autoencoder for Unsupervised Multivariate Time Series Representation Learning
- 设计双重掩码任务：重建可见数据与预测被掩码特征的潜在表示。
- 在多个下游任务中优于现有基线，实现更优的分类、回归和预测性能。
- 适合需要无标签时间序列建模的研究者，尤其关注表示学习与迁移能力。
无监督多变量时间序列（MTS）表示学习旨在从原始序列中提取紧凑且信息丰富的表示，无需依赖标签，从而高效迁移到多种下游任务。本文提出双掩码自编码器（DMAE），一种新颖的无监督MTS表示学习框架。DMAE设计两个互补的预训练任务：(1) 基于可见属性重建被掩码值；(2) 在教师编码器引导下估计被掩码特征的潜在表示。为进一步提升表示质量，引入特征级对齐约束，促使预测的潜在表示与教师输出对齐。通过联合优化这些目标，DMAE学习到具有时序一致性和语义丰富性的表示。在分类、回归和预测任务上的全面评估表明，该方法在多个基准上均取得一致且优越的性能。
原文摘要 · Abstract (English)
Unsupervised multivariate time series (MTS) representation learning aims to extract compact and informative representations from raw sequences without relying on labels, enabling efficient transfer to diverse downstream tasks. In this paper, we propose Dual-Masked Autoencoder (DMAE), a novel masked time-series modeling framework for unsupervised MTS representation learning. DMAE formulates two complementary pretext tasks: (1) reconstructing masked values based on visible attributes, and (2) estimating latent representations of masked features, guided by a teacher encoder. To further improve representation quality, we introduce a feature-level alignment constraint that encourages the predicted latent representations to align with the teacher's outputs. By jointly optimizing these objectives, DMAE learns temporally coherent and semantically rich representations. Comprehensive evaluations across classification, regression, and forecasting tasks demonstrate that our approach achieves consistent and superior performance over competitive baselines.
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。