Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in the absence of expert annotations. However, existing contrastive approaches generally treat each instance independently, which leads to false negative pairs that share the same semantics. To tackle this problem, we propose MHCCL, a Masked Hierarchical Cluster-wise Contrastive Learning model, which exploits semantic information obtained from the hierarchical structure consisting of multiple latent partitions for multivariate time series. Motivated by the observation that fine-grained clustering preserves higher purity while coarse-grained one reflects higher-level semantics, we propose a novel downward masking strategy to filter out fake negatives and supplement positives by incorporating the multi-granularity information from the clustering hierarchy. In addition, a novel upward masking strategy is designed in MHCCL to remove outliers of clusters at each partition to refine prototypes, which helps speed up the hierarchical clustering process and improves the clustering quality. We conduct experimental evaluations on seven widely-used multivariate time series datasets. The results demonstrate the superiority of MHCCL over the state-of-the-art approaches for unsupervised time series representation learning.

翻译：从原始无标注时间序列数据中学习语义丰富的表征，对分类和预测等下游任务至关重要。对比学习近期在缺乏专家标注的情况下展现了其强大的表征学习能力。然而，现有的对比方法通常独立处理每个实例，导致共享相同语义的假负样本对出现。为解决这一问题，我们提出了MHCCL——一种掩码层次聚类对比学习模型，该模型利用从多元时间序列的多个潜在划分构成的层次结构中获取的语义信息。受细粒度聚类保持更高纯度而粗粒度聚类反映高层语义这一观察的启发，我们提出了一种新颖的下行掩码策略，通过整合聚类层次中的多粒度信息来过滤假负样本并补充正样本。此外，MHCCL设计了一种新颖的上行掩码策略，用于移除每个划分中聚类中的异常点以精炼原型，这有助于加速层次聚类过程并提升聚类质量。我们在七个广泛使用的多元时间序列数据集上进行了实验评估，结果表明MHCCL在无监督时间序列表征学习方面优于最先进的方法。