时间序列的软对比学习
Soft Contrastive Learning for Time Series
AI总结：
SoftCLT通过引入实例级和时间级对比损失，提升时间序列表示学习的质量，适用于多种下游任务。
摘要：
对比学习在以自监督方式从时间序列中学习表示方面已被证明是有效的。然而，对比相似的时间序列实例或相邻时间戳内的值会导致忽略其内在相关性，从而降低学习到的表示质量。为了解决这个问题，我们提出了SoftCLT，一种简单而有效的软对比学习策略用于时间序列。这是通过引入实例级和时间级对比损失以及范围从零到一的软分配来实现的。具体来说，我们通过数据空间中时间序列之间的距离定义实例级对比损失的软分配，通过时间戳的差异定义时间级对比损失的软分配。SoftCLT是一种即插即用的时间序列对比学习方法，无需额外的复杂性即可提高学习到的表示质量。在实验中，我们证明SoftCLT在各种下游任务中，包括分类、半监督学习、迁移学习和异常检测，都一致地提高了性能，显示出最先进的性能。代码可在此仓库中获得：https://github.com/seunghan96/softclt。
英文摘要：
Contrastive learning has shown to be effective to learn representations from time series in a self-supervised way. However, contrasting similar time series instances or values from adjacent timestamps within a time series leads to ignore their inherent correlations, which results in deteriorating the quality of learned representations. To address this issue, we propose SoftCLT, a simple yet effective soft contrastive learning strategy for time series. This is achieved by introducing instance-wise and temporal contrastive loss with soft assignments ranging from zero to one. Specifically, we define soft assignments for 1) instance-wise contrastive loss by the distance between time series on the data space, and 2) temporal contrastive loss by the difference of timestamps. SoftCLT is a plug-and-play method for time series contrastive learning that improves the quality of learned representations without bells and whistles. In experiments, we demonstrate that SoftCLT consistently improves the performance in various downstream tasks including classification, semi-supervised learning, transfer learning, and anomaly detection, showing state-of-the-art performance. Code is available at this repository: https://github.com/seunghan96/softclt.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
