A Co-training Approach for Noisy Time Series Learning
This addresses noise robustness in time series analysis for domains like finance or healthcare, but it appears incremental as it builds on existing contrastive learning and co-training methods.
The paper tackles robust time series representation learning by proposing a co-training approach with two encoders to leverage complementary views, mitigating noise impact and achieving significant performance improvements on four benchmarks in unsupervised and semi-supervised settings.
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.