mlsanityData to 14 Oct 2026

Label-efficient Time Series Representation Learning: A Review

arXiv 2302.06433 ↗First posted 13 Feb 2023cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time series data, various strategies, e.g., transfer learning, self-supervised learning, and semi-supervised learning, have been developed. In this survey, we introduce a novel taxonomy for the first time, categorizing existing approaches as in-domain or cross-domain, based on their reliance on external data sources or not. Furthermore, we present a review of the recent advances in each strategy, conclude the limitations of current methodologies, and suggest future research directions that promise further improvements in the field.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 52 of its 118 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

52 of 118 references.

References · 52

  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. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  6. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  8. 2014How transferable are features in deep neural networks?cited by 1,225
  9. 2018Deep learning for time series classification: a reviewcited by 576
  10. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 471
  11. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 453
  12. 2015Return of Frustratingly Easy Domain Adaptationcited by 391
38 more
  1. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 387
  2. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 360
  3. 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 345
  4. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 250
  5. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 226
  6. 2021Unsupervised Representation Learning for Time Series with Temporal Neighborhood Codingcited by 224
  7. 2017DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEGcited by 157
  8. 2020An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networkscited by 128
  9. 2020Uncovering the structure of clinical EEG signals with self-supervised learningcited by 109
  10. 2019Multi-task Self-Supervised Learning for Human Activity Detectioncited by 102
  11. 2020Self-supervised ECG Representation Learning for Emotion Recognitioncited by 99
  12. 2021Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Seriescited by 96
  13. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  14. 2020Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Datacited by 82
  15. 2021Domain Adaptation for Time Series Forecasting via Attention Sharingcited by 68
  16. 2018Transfer learning for time series classificationcited by 60
  17. 2023Domain Adaptation for Time Series Under Feature and Label Shiftscited by 60
  18. 2022Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Seriescited by 54
  19. 2020Time Series Domain Adaptation via Sparse Associative Structure Alignmentcited by 51
  20. 2020Omni-Scale CNNs: a simple and effective kernel size configuration for time series classificationcited by 48
  21. 2022ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Datacited by 45
  22. 2022Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classificationcited by 39
  23. 2021Self-supervised Autoregressive Domain Adaptation for Time Series Datacited by 29
  24. 2022MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Seriescited by 28
  25. 2021Self-supervised Contrastive Learning for EEG-based Sleep Stagingcited by 27
  26. 2022Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Datacited by 27
  27. 2018EA-LSTM: Evolutionary Attention-based LSTM for Time Series Predictioncited by 26
  28. 2022Domain Adaptation for Time-Series Classification to Mitigate Covariate Shiftcited by 24
  29. 2020Sense and Learn: Self-Supervision for Omnipresent Sensorscited by 21
  30. 2022Contrastive Domain Adaptation for Time-Series via Temporal Mixupcited by 18
  31. 2019Multi-Resolution Weak Supervision for Sequential Datacited by 17
  32. 2021ADAST: Attentive Cross-domain EEG-based Sleep Staging Framework with Iterative Self-Trainingcited by 17
  33. 2022Utilizing Expert Features for Contrastive Learning of Time-Series Representationscited by 17
  34. 2020Transfer Learning for Human Activity Recognition using Representational Analysis of Neural Networkscited by 14
  35. 2022Self-supervised Learning for Label-Efficient Sleep Stage Classification: A Comprehensive Evaluationcited by 14
  36. 2021Deep Bregman Divergence for Contrastive Learning of Visual Representationscited by 13
  37. 2022PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognitioncited by 12
  38. 2021SMATE: Semi-Supervised Spatio-Temporal Representation Learning on Multivariate Time Seriescited by 9

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 5; 2026: 4.

16 papers.

Sort:

By area:

  1. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 99
  2. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  3. 2024Universal Time-Series Representation Learning: A Surveycited by 30
  4. 2023Graph-Aware Contrasting for Multivariate Time-Series Classificationcited by 11
  5. 2024Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Maskcited by 10
  6. 2024HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling with Self-Distillation for Long-Term Forecastingcited by 8
  7. 2025Cross-Domain Conditional Diffusion Models for Time Series Imputationcited by 4
  8. 2025PromptTSS: A Prompting-Based Approach for Interactive Multi-Granularity Time Series Segmentationcited by 2
  9. 2024An Active Learning Framework with a Class Balancing Strategy for Time Series Classificationcited by 0
  10. 2025SimDeep: Federated 3D Indoor Localization via Similarity-Aware Aggregationcited by 0
  11. 2025Perseus: Interactive Time Series Segmentation with Sparse Supervision via Stateful Memorycited by 0
  12. 2025Weighted Contrastive Learning for Anomaly-Aware Time-Series Forecastingcited by 0
4 more
  1. 2026Let Experts Feel Uncertainty: A Multi-Expert Label Distribution Approach to Probabilistic Time Series Forecastingcited by 0
  2. 2026Self-Supervised Learning via Flow-Guided Neural Operator on Time-Series Datacited by 0
  3. 2026EvoTSC: Evolving Feature Learning Models for Time Series Classification via Genetic Programmingcited by 0
  4. 2026Progressive Memory Transformer: Memory-Aware Attention for Time-Seriescited by 0