mlsanityData to 14 Oct 2026

A Co-training Approach for Noisy Time Series Learning

arXiv 2308.12551 ↗First posted 24 Aug 2023cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 31 of its 59 references that are in the map. First posted on arXiv 24 Aug 2023.

Builds on

31 of 59 references.

References · 31

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  4. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  5. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  6. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  7. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 471
  8. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 453
  9. 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 345
  10. 2021Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Losscited by 313
  11. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 250
  12. 2020Self-supervised Co-training for Video Representation Learningcited by 232
19 more
  1. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 226
  2. 2021Unsupervised Representation Learning for Time Series with Temporal Neighborhood Codingcited by 224
  3. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 144
  4. 2021AdaRNN: Adaptive Learning and Forecasting of Time Seriescited by 121
  5. 2022Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecastingcited by 117
  6. 20213D Human Action Representation Learning via Cross-View Consistency Pursuitcited by 106
  7. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  8. 2020Exploring Contrastive Learning in Human Activity Recognition for Healthcarecited by 75
  9. 2022Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Versioncited by 59
  10. 2023Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Seriescited by 55
  11. 2019Predicting Path Failure In Time-Evolving Graphscited by 54
  12. 2022Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Seriescited by 54
  13. 2022TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysiscited by 48
  14. 2022Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecastingcited by 36
  15. 2021Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filteringcited by 31
  16. 2022Robust Probabilistic Time Series Forecastingcited by 15
  17. 2022Robust Time Series Denoising with Learnable Wavelet Packet Transformcited by 10
  18. 2022Residual Correction in Real-Time Traffic Forecastingcited by 8
  19. 2023An Iterative Wavelet Threshold for Signal Denoisingcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 4; 2025: 2.

8 papers.

  1. 2023ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizonscited by 36
  2. 2024Universal Time-Series Representation Learning: A Surveycited by 30
  3. 2024MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learningcited by 11
  4. 2024Weakly Supervised Anomaly Detection via Knowledge-Data Alignmentcited by 10
  5. 2024Denoising-Aware Contrastive Learning for Noisy Time Seriescited by 5
  6. 2025Mamba time series forecasting with uncertainty quantificationcited by 2
  7. 2023Multi-Scale and Multi-Modal Contrastive Learning Network for Biomedical Time Seriescited by 1
  8. 2025Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistencycited by 1