Denoising-Aware Contrastive Learning for Noisy Time Series

TL;DR

This paper introduces Denoising-Aware Contrastive Learning (DECL), a novel SSL approach for noisy time series that automatically mitigates noise effects during representation learning, outperforming traditional pre-processing methods.

Contribution

The paper proposes a contrastive learning framework that adaptively handles noise in time series data, eliminating the need for manual denoising pre-processing.

Findings

DECL improves robustness against noise in time series.

The method outperforms traditional denoising pre-processing approaches.

Extensive experiments validate its effectiveness across datasets.

Abstract

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.