Denoising-Aware Contrastive Learning for Noisy Time Series
This addresses noise issues in time series SSL for applications like forecasting or anomaly detection, but it is incremental as it builds on existing contrastive learning methods.
The paper tackles the problem of noise in time series self-supervised learning, which impairs performance, by proposing denoising-aware contrastive learning (DECL) that mitigates noise in representations and automatically selects denoising methods, achieving effectiveness verified through extensive experiments on various datasets.
Time series self-supervised learning (SSL) aims to exploit unlabeled data for pre-training to mitigate the reliance on labels. Despite the great success in recent years, there is limited discussion on the potential noise in the time series, which can severely impair the performance of existing SSL methods. To mitigate the noise, the de facto strategy is to apply conventional denoising methods before model training. However, this pre-processing approach may not fully eliminate the effect of noise in SSL for two reasons: (i) the diverse types of noise in time series make it difficult to automatically determine suitable denoising methods; (ii) noise can be amplified after mapping raw data into latent space. In this paper, we propose denoising-aware contrastive learning (DECL), which uses contrastive learning objectives to mitigate the noise in the representation and automatically selects suitable denoising methods for every sample. Extensive experiments on various datasets verify the effectiveness of our method. The code is open-sourced.