mlsanityData to 7 Oct 2026

Unsupervised Scalable Representation Learning for Multivariate Time Series

arXiv 1901.10738 ↗First posted 30 Jan 2019cs.LG cs.NE stat.MLcited by 267

Not on the map. Why?

Abstract (arXiv)

Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn universal embeddings of time series. Unlike previous works, it is scalable with respect to their length and we demonstrate the quality, transferability and practicability of the learned representations with thorough experiments and comparisons. To this end, we combine an encoder based on causal dilated convolutions with a novel triplet loss employing time-based negative sampling, obtaining general-purpose representations for variable length and multivariate time series.

Key facts. Cited by 267 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 28; 2023: 63; 2024: 66; 2025: 64; 2026: 17.

267 papers.

Sort:

By area:

  1. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  2. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  3. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  4. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
  5. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 453
  6. 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 342
  7. 2021Unsupervised Representation Learning for Time Series with Temporal Neighborhood Codingcited by 223
  8. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 165
  9. 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 147
  10. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 143
  11. 2024TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysiscited by 113
  12. 2023SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modelingcited by 112
38 more
  1. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 102
  2. 2023The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecastingcited by 100
  3. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  4. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  5. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  6. 2021Chaos as an interpretable benchmark for forecasting and data-driven modellingcited by 87
  7. 2023Time Series as Images: Vision Transformer for Irregularly Sampled Time Seriescited by 79
  8. 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusioncited by 75
  9. 2022Flowformer: Linearizing Transformers with Conservation Flowscited by 69
  10. 2023Deep Learning for Time Series Classification and Extrinsic Regression: A Current Surveycited by 68
  11. 2023Ti-MAE: Self-Supervised Masked Time Series Autoencoderscited by 63
  12. 2024TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecastingcited by 63
  13. 2023Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Seriescited by 59
  14. 2021PSA-GAN: Progressive Self Attention GANs for Synthetic Time Seriescited by 58
  15. 2022Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Seriescited by 54
  16. 2023SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecastingcited by 53
  17. 2023Time Series Contrastive Learning with Information-Aware Augmentationscited by 52
  18. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  19. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 49
  20. 2023Soft Contrastive Learning for Time Seriescited by 49
  21. 2022Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformercited by 47
  22. 2021Neural Contextual Anomaly Detection for Time Seriescited by 42
  23. 2023TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoderscited by 42
  24. 2022Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classificationcited by 39
  25. 2024TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysiscited by 37
  26. 2022Contrastive Learning for Unsupervised Domain Adaptation of Time Seriescited by 36
  27. 2021Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signalscited by 35
  28. 2023Learning to Embed Time Series Patches Independentlycited by 34
  29. 2025Context-Alignment: Activating and Enhancing LLM Capabilities in Time Seriescited by 34
  30. 2021Neighborhood Contrastive Learning Applied to Online Patient Monitoringcited by 32
  31. 2023FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Spacecited by 31
  32. 2021Self-supervised EEG Representation Learning for Automatic Sleep Stagingcited by 30
  33. 2022MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Seriescited by 28
  34. 2024Universal Time-Series Representation Learning: A Surveycited by 28
  35. 2022Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Datacited by 27
  36. 2024Heterogeneous Contrastive Learning for Foundation Models and Beyondcited by 27
  37. 2023MBrain: A Multi-channel Self-Supervised Learning Framework for Brain Signalscited by 26
  38. 2023BrainNet: Epileptic Wave Detection from SEEG with Hierarchical Graph Diffusion Learningcited by 25

50 most cited of 267 All 267 (JSON)