Denoising-Aware Contrastive Learning for Noisy Time Series

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Shuang, Zha, Daochen, Shen, Xiao, Huang, Xiao, Zhang, Rui, Chung, Fu-Lai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911909952880640
author Zhou, Shuang
Zha, Daochen
Shen, Xiao
Huang, Xiao
Zhang, Rui
Chung, Fu-Lai
author_facet Zhou, Shuang
Zha, Daochen
Shen, Xiao
Huang, Xiao
Zhang, Rui
Chung, Fu-Lai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_04627
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Denoising-Aware Contrastive Learning for Noisy Time Series
Zhou, Shuang
Zha, Daochen
Shen, Xiao
Huang, Xiao
Zhang, Rui
Chung, Fu-Lai
Machine Learning
Artificial Intelligence
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.
title Denoising-Aware Contrastive Learning for Noisy Time Series
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.04627