mlsanityData to 7 Oct 2026

Simple Contrastive Representation Learning for Time Series Forecasting

arXiv 2303.18205 ↗First posted 31 Mar 2023cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Contrastive learning methods have shown an impressive ability to learn meaningful representations for image or time series classification. However, these methods are less effective for time series forecasting, as optimization of instance discrimination is not directly applicable to predicting the future state from the historical context. To address these limitations, we propose SimTS, a simple representation learning approach for improving time series forecasting by learning to predict the future from the past in the latent space. SimTS exclusively uses positive pairs and does not depend on negative pairs or specific characteristics of a given time series. In addition, we show the shortcomings of the current contrastive learning framework used for time series forecasting through a detailed ablation study. Overall, our work suggests that SimTS is a promising alternative to other contrastive learning approaches for time series forecasting.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 31 Mar 2023.

Builds on

29 of 38 references.

References · 29

  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. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  7. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  8. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  9. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  10. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  11. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  12. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
17 more
  1. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  2. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  3. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  4. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
  5. 2016Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICAcited by 270
  6. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 267
  7. 2021Understanding self-supervised Learning Dynamics without Contrastive Pairscited by 254
  8. 2021Unsupervised Representation Learning for Time Series with Temporal Neighborhood Codingcited by 223
  9. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  10. 2020CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patientscited by 170
  11. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 143
  12. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  13. 2022How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learningcited by 65
  14. 2023Time Series Contrastive Learning with Information-Aware Augmentationscited by 52
  15. 2021Neighborhood Contrastive Learning Applied to Online Patient Monitoringcited by 32
  16. 2022Preformer: Predictive Transformer with Multi-Scale Segment-wise Correlations for Long-Term Time Series Forecastingcited by 23
  17. 2022Utilizing Expert Features for Contrastive Learning of Time-Series Representationscited by 17

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3; 2025: 1.

7 papers.

  1. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 165
  2. 2023TimeDRL: Disentangled Representation Learning for Multivariate Time-Seriescited by 10
  3. 2023What Constitutes Good Contrastive Learning in Time-Series Forecasting?cited by 2
  4. 2024Self-Supervised Learning of Disentangled Representations for Multivariate Time-Seriescited by 2
  5. 2024EXCON: Extreme Instance-based Contrastive Representation Learning of Severely Imbalanced Multivariate Time Series for Solar Flare Predictioncited by 2
  6. 2024SiamTST: A Novel Representation Learning Framework for Enhanced Multivariate Time Series Forecasting applied to Telco Networkscited by 0
  7. 2025MTS-DMAE: Dual-Masked Autoencoder for Unsupervised Multivariate Time Series Representation Learningcited by 0