mlsanityData to 14 Oct 2026

Unsupervised Representation Learning for Time Series: A Review

arXiv 2308.01578 ↗First posted 3 Aug 2023cs.LG cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

Unsupervised representation learning approaches aim to learn discriminative feature representations from unlabeled data, without the requirement of annotating every sample. Enabling unsupervised representation learning is extremely crucial for time series data, due to its unique annotation bottleneck caused by its complex characteristics and lack of visual cues compared with other data modalities. In recent years, unsupervised representation learning techniques have advanced rapidly in various domains. However, there is a lack of systematic analysis of unsupervised representation learning approaches for time series. To fill the gap, we conduct a comprehensive literature review of existing rapidly evolving unsupervised representation learning approaches for time series. Moreover, we also develop a unified and standardized library, named ULTS (i.e., Unsupervised Learning for Time Series), to facilitate fast implementations and unified evaluations on various models. With ULTS, we empirically evaluate state-of-the-art approaches, especially the rapidly evolving contrastive learning methods, on 9 diverse real-world datasets. We further discuss practical considerations as well as open research challenges on unsupervised representation learning for time series to facilitate future research in this field.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 107 of its 149 references that are in the map. First posted on arXiv 3 Aug 2023.

Builds on

107 of 149 references.

References · 107

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  9. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  10. 2014Conditional Generative Adversarial Netscited by 2,162
  11. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  12. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
38 more
  1. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  2. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  3. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  4. 2020What Makes for Good Views for Contrastive Learning?cited by 846
  5. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  6. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  7. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  8. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  9. 2017Wasserstein GANcited by 639
  10. 2017Generative Adversarial Networks: An Overviewcited by 590
  11. 2018Deep learning for time series classification: a reviewcited by 576
  12. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 471
  13. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 453
  14. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 387
  15. 2020Spatiotemporal Contrastive Video Representation Learningcited by 372
  16. 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 345
  17. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
  18. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 326
  19. 2016Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICAcited by 273
  20. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 273
  21. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 269
  22. 2020Contrastive Clusteringcited by 265
  23. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 260
  24. 2021Understanding self-supervised Learning Dynamics without Contrastive Pairscited by 256
  25. 2019Revisiting Self-Supervised Visual Representation Learningcited by 251
  26. 2019Fast AutoAugmentcited by 243
  27. 2019Large Scale Adversarial Representation Learningcited by 239
  28. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 226
  29. 2020What Should Not Be Contrastive in Contrastive Learningcited by 226
  30. 2021Unsupervised Representation Learning for Time Series with Temporal Neighborhood Codingcited by 224
  31. 2021Contrastive Learning Inverts the Data Generating Processcited by 221
  32. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  33. 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
  34. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  35. 2020Benchmarking Multivariate Time Series Classification Algorithmscited by 145
  36. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 144
  37. 2018Scaling provable adversarial defensescited by 143
  38. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 142

50 most cited of 107 All 107 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 6; 2025: 4; 2026: 1.

14 papers.

Sort:

By area:

  1. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 169
  2. 2023LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasterscited by 129
  3. 2025Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settingscited by 37
  4. 2024A Survey of Deep Learning and Foundation Models for Time Series Forecastingcited by 33
  5. 2024Universal Time-Series Representation Learning: A Surveycited by 30
  6. 2024Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Maskcited by 10
  7. 2024Radio Foundation Models: Pre-training Transformers for 5G-based Indoor Localizationcited by 10
  8. 2024Denoising-Aware Contrastive Learning for Noisy Time Seriescited by 5
  9. 2025Representation Learning of Limit Order Book: A Comprehensive Study and Benchmarkingcited by 2
  10. 2025FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classificationcited by 2
  11. 2024Review of Data-centric Time Series Analysis from Sample, Feature, and Periodcited by 1
  12. 2023Unsupervised Multi-modal Feature Alignment for Time Series Representation Learningcited by 0
2 more
  1. 2025Water Demand Forecasting of District Metered Areas through Learned Consumer Representationscited by 0
  2. 2026FMMVCC: Fuzzy Mamba-based Multi-View Contrastive Clustering for Univariate Time Seriescited by 0