In this work, we focus on robust time series representation learning. Our assumption is that real-world time series is noisy and complementary information from different views of the same time series plays an important role while analyzing noisy input. Based on this, we create two views for the input time series through two different encoders. We conduct co-training based contrastive learning iteratively to learn the encoders. Our experiments demonstrate that this co-training approach leads to a significant improvement in performance. Especially, by leveraging the complementary information from different views, our proposed TS-CoT method can mitigate the impact of data noise and corruption. Empirical evaluations on four time series benchmarks in unsupervised and semi-supervised settings reveal that TS-CoT outperforms existing methods. Furthermore, the representations learned by TS-CoT can transfer well to downstream tasks through fine-tuning.

翻译：在这项工作中，我们专注于鲁棒的时间序列表示学习。我们的假设是，现实世界中的时间序列数据包含噪声，而同一时间序列不同视角下的互补信息在分析含噪输入时起着重要作用。基于此，我们通过两个不同的编码器为输入时间序列创建两个视角。我们迭代地进行基于协同训练的对比学习来训练编码器。实验表明，这种协同训练方法能够显著提升性能。特别是，通过利用不同视角的互补信息，我们提出的TS-CoT方法可以缓解数据噪声和损坏的影响。在无监督和半监督设置下对四个时间序列基准数据集的实证评估显示，TS-CoT优于现有方法。此外，通过微调，TS-CoT学习到的表示能够很好地迁移到下游任务中。