mlsanityData to 7 Oct 2026

Utilizing Expert Features for Contrastive Learning of Time-Series Representations

arXiv 2206.11517 ↗First posted 23 Jun 2022cs.LG cs.AI stat.MLcited by 17

Not on the map. Why?

Abstract (arXiv)

We present an approach that incorporates expert knowledge for time-series representation learning. Our method employs expert features to replace the commonly used data transformations in previous contrastive learning approaches. We do this since time-series data frequently stems from the industrial or medical field where expert features are often available from domain experts, while transformations are generally elusive for time-series data. We start by proposing two properties that useful time-series representations should fulfill and show that current representation learning approaches do not ensure these properties. We therefore devise ExpCLR, a novel contrastive learning approach built on an objective that utilizes expert features to encourage both properties for the learned representation. Finally, we demonstrate on three real-world time-series datasets that ExpCLR surpasses several state-of-the-art methods for both unsupervised and semi-supervised representation learning.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 31 of its 41 references that are in the map. First posted on arXiv 23 Jun 2022.

Builds on

31 of 41 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  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. 2020Supervised Contrastive Learningcited by 2,803
  7. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  8. 2020Knowledge Distillation: A Surveycited by 1,578
  9. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  10. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  11. 2019Relational Knowledge Distillationcited by 873
  12. 2020What Makes for Good Views for Contrastive Learning?cited by 843
19 more
  1. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
  2. 2020Understanding the Behaviour of Contrastive Losscited by 397
  3. 2020Debiased Contrastive Learningcited by 354
  4. 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 342
  5. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  6. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 267
  7. 2021Unsupervised Representation Learning for Time Series with Temporal Neighborhood Codingcited by 223
  8. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  9. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  10. 2020An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networkscited by 128
  11. 2021Weakly Supervised Contrastive Learningcited by 81
  12. 2020Viewmaker Networks: Learning Views for Unsupervised Representation Learningcited by 48
  13. 2019Learning Metrics from Teachers: Compact Networks for Image Embeddingcited by 38
  14. 2019Deep Metric Learning Beyond Binary Supervisioncited by 36
  15. 2020Task Programming: Learning Data Efficient Behavior Representationscited by 27
  16. 2021Embedding Transfer with Label Relaxation for Improved Metric Learningcited by 21
  17. 2021Contrastive Neural Processes for Self-Supervised Learningcited by 9
  18. 2021SleepPriorCL: Contrastive Representation Learning with Prior Knowledge-based Positive Mining and Adaptive Temperature for Sleep Stagingcited by 6
  19. 2019KINN: Incorporating Expert Knowledge in Neural Networkscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 5; 2025: 2; 2026: 1.

17 papers.

Sort:

By area:

  1. 2023SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modelingcited by 112
  2. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  3. 2023Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Seriescited by 59
  4. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  5. 2023FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Spacecited by 31
  6. 2023Label-efficient Time Series Representation Learning: A Reviewcited by 16
  7. 2023Unsupervised Representation Learning for Time Series: A Reviewcited by 14
  8. 2022Supervised Contrastive Learning with Hard Negative Samplescited by 13
  9. 2024Parametric Augmentation for Time Series Contrastive Learningcited by 12
  10. 2023Simple Contrastive Representation Learning for Time Series Forecastingcited by 7
  11. 2024Denoising-Aware Contrastive Learning for Noisy Time Seriescited by 5
  12. 2024Self-Supervised Learning for Time Series: Contrastive or Generative?cited by 4
5 more
  1. 2024From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signalscited by 4
  2. 2024PreMixer: MLP-Based Pre-training Enhanced MLP-Mixers for Large-scale Traffic Forecastingcited by 2
  3. 2025How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reductioncited by 1
  4. 2025Learning Time-Series Representations by Hierarchical Uniformity-Tolerance Latent Balancingcited by 1
  5. 2026Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAscited by 1