mlsanityData to 7 Oct 2026

Denoising-Aware Contrastive Learning for Noisy Time Series

arXiv 2406.04627 ↗First posted 7 Jun 2024cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 32 of its 74 references that are in the map. First posted on arXiv 7 Jun 2024.

Builds on

32 of 74 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2018Deep learning for time series classification: a reviewcited by 575
  5. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
  6. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
  7. 2018The UCR Time Series Archivecited by 421
  8. 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 342
  9. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 246
  10. 2021Unsupervised Representation Learning for Time Series with Temporal Neighborhood Codingcited by 223
  11. 2020CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patientscited by 170
  12. 2023SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modelingcited by 112
20 more
  1. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  2. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  3. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  4. 2020Time Series Change Point Detection with Self-Supervised Contrastive Predictive Codingcited by 58
  5. 2021PSA-GAN: Progressive Self Attention GANs for Synthetic Time Seriescited by 58
  6. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  7. 2022Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformercited by 47
  8. 2022GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networkscited by 43
  9. 2020Learning from Irregularly-Sampled Time Series: A Missing Data Perspectivecited by 40
  10. 2022Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classificationcited by 39
  11. 2021Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signalscited by 35
  12. 2021Neighborhood Contrastive Learning Applied to Online Patient Monitoringcited by 32
  13. 2020EEGdenoiseNet: A benchmark dataset for end-to-end deep learning solutions of EEG denoisingcited by 31
  14. 2022MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Seriescited by 28
  15. 2022Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN)cited by 23
  16. 2022Utilizing Expert Features for Contrastive Learning of Time-Series Representationscited by 17
  17. 2022Robust Probabilistic Time Series Forecastingcited by 15
  18. 2023Unsupervised Representation Learning for Time Series: A Reviewcited by 14
  19. 2022Detecting Anomalies within Time Series using Local Neural Transformationscited by 12
  20. 2023A Co-training Approach for Noisy Time Series Learningcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculumcited by 3
  2. 2025Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistencycited by 1
  3. 2025Transformer Modeling for Both Scalability and Performance in Multivariate Time Seriescited by 0
  4. 2025Towards Foundation Models for Cryo-ET Subtomogram Analysiscited by 0
  5. 2026Deep Time-Series Forecasting in 10 Years: A Surveycited by 0