mlsanityData to 7 Oct 2026

Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

arXiv 2310.14017 ↗First posted 21 Oct 2023cs.LG cs.AIcited by 59

Not on the map. Why?

Abstract (arXiv)

Contrastive representation learning is crucial in medical time series analysis as it alleviates dependency on labor-intensive, domain-specific, and scarce expert annotations. However, existing contrastive learning methods primarily focus on one single data level, which fails to fully exploit the intricate nature of medical time series. To address this issue, we present COMET, an innovative hierarchical framework that leverages data consistencies at all inherent levels in medical time series. Our meticulously designed model systematically captures data consistency from four potential levels: observation, sample, trial, and patient levels. By developing contrastive loss at multiple levels, we can learn effective representations that preserve comprehensive data consistency, maximizing information utilization in a self-supervised manner. We conduct experiments in the challenging patient-independent setting. We compare COMET against six baselines using three diverse datasets, which include ECG signals for myocardial infarction and EEG signals for Alzheimer's and Parkinson's diseases. The results demonstrate that COMET consistently outperforms all baselines, particularly in setup with 10% and 1% labeled data fractions across all datasets. These results underscore the significant impact of our framework in advancing contrastive representation learning techniques for medical time series. The source code is available at https://github.com/DL4mHealth/COMET.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 25 of its 53 references that are in the map. First posted on arXiv 21 Oct 2023.

Builds on

25 of 53 references.

References · 25

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  4. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  5. 2016Colorful Image Colorizationcited by 1,113
  6. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  7. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
  8. 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 342
  9. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 267
  10. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 246
  11. 2021Unsupervised Representation Learning for Time Series with Temporal Neighborhood Codingcited by 223
  12. 2020CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patientscited by 170
13 more
  1. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
  2. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  3. 2021Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysiscited by 75
  4. 2020Exploring Contrastive Learning in Human Activity Recognition for Healthcarecited by 73
  5. 2022Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Seriescited by 54
  6. 2022End-to-End Human-Gaze-Target Detection with Transformerscited by 47
  7. 2021Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signalscited by 35
  8. 2021Neighborhood Contrastive Learning Applied to Online Patient Monitoringcited by 32
  9. 2023ManyDG: Many-domain Generalization for Healthcare Applicationscited by 23
  10. 2022Utilizing Expert Features for Contrastive Learning of Time-Series Representationscited by 17
  11. 2021Discovery of Single Independent Latent Variablecited by 3
  12. 2022Medusa: Universal Feature Learning via Attentional Multitaskingcited by 1
  13. 2022Contrastive Graph Few-Shot Learningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 27; 2025: 20; 2026: 12.

59 papers.

Sort:

By area:

  1. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  2. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  3. 2024Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classificationcited by 53
  4. 2024Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfercited by 31
  5. 2024Towards Neural Scaling Laws for Time Series Foundation Modelscited by 30
  6. 2024Universal Time-Series Representation Learning: A Surveycited by 28
  7. 2025LightGTS: A Lightweight General Time Series Forecasting Modelcited by 28
  8. 2025Aurora: Towards Universal Generative Multimodal Time Series Forecastingcited by 28
  9. 2025CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variablescited by 21
  10. 2024TimeSiam: A Pre-Training Framework for Siamese Time-Series Modelingcited by 20
  11. 2024Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Modelscited by 17
  12. 2024Medical Multimodal Foundation Models in Clinical Diagnosis and Treatment: Applications, Challenges, and Future Directionscited by 17
38 more
  1. 2024An Open and Large-Scale Dataset for Multi-Modal Climate Change-aware Crop Yield Predictionscited by 11
  2. 2024MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learningcited by 11
  3. 2024Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learningcited by 9
  4. 2025MedGNN: Towards Multi-resolution Spatiotemporal Graph Learning for Medical Time Series Classificationcited by 9
  5. 2024CREMA: A Contrastive Regularized Masked Autoencoder for Robust ECG Diagnostics across Clinical Domainscited by 8
  6. 2025LEAD: An EEG Foundation Model for Alzheimer's Disease Detectioncited by 8
  7. 2024ADAPT: Multimodal Learning for Detecting Physiological Changes under Missing Modalitiescited by 6
  8. 2024Toward Robust Early Detection of Alzheimer's Disease via an Integrated Multimodal Learning Approachcited by 6
  9. 2024Repurposing Foundation Model for Generalizable Medical Time Series Classificationcited by 6
  10. 2024UniCL: A Universal Contrastive Learning Framework for Large Time Series Modelscited by 5
  11. 2024Guidelines for Augmentation Selection in Contrastive Learning for Time Series Classificationcited by 5
  12. 2024EMIT- Event-Based Masked Auto Encoding for Irregular Time Seriescited by 5
  13. 2026Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Seriescited by 5
  14. 2025Fuzzy Cluster-Aware Contrastive Clustering for Time Seriescited by 4
  15. 2025Multi-View Contrastive Learning for Robust Domain Adaptation in Medical Time Series Analysiscited by 4
  16. 2024Scalable Transformer for High Dimensional Multivariate Time Series Forecastingcited by 3
  17. 2025FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecastingcited by 3
  18. 2026Cross-Subject Generalization for EEG Decoding: A Survey of Deep Learning Methodscited by 3
  19. 2024EEG-MACS: Manifold Attention and Confidence Stratification for EEG-based Cross-Center Brain Disease Diagnosis under Unreliable Annotationscited by 2
  20. 2024Nonlinear time-series embedding by monotone variational inequalitycited by 2
  21. 2024Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecastingcited by 2
  22. 2024StatioCL: Contrastive Learning for Time Series via Non-Stationary and Temporal Contrastcited by 2
  23. 2025EEG-ReMinD: Enhancing Neurodegenerative EEG Decoding through Self-Supervised State Reconstruction-Primed Riemannian Dynamicscited by 2
  24. 2025Beyond Fixed Variables: Expanding-variate Time Series Forecasting via Flat Scheme and Spatio-temporal Focal Learningcited by 2
  25. 2025Skin Lesion Phenotyping via Nested Multi-modal Contrastive Learningcited by 2
  26. 2024ADformer: A Multi-Granularity Spatial-Temporal Transformer for EEG-Based Alzheimer Detectioncited by 1
  27. 2025Smarter Together: Combining Large Language Models and Small Models for Physiological Signals Visual Inspectioncited by 1
  28. 2025Structure-preserving contrastive learning for spatial time seriescited by 1
  29. 2025Efficient Hierarchical Contrastive Self-supervising Learning for Time Series Classification via Importance-aware Resolution Selectioncited by 1
  30. 2025Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generationcited by 1
  31. 2025Enhancing Contrastive Learning-based Electrocardiogram Pretrained Model with Patient Memory Queuecited by 1
  32. 2025PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Seriescited by 1
  33. 2025Domain Knowledge is Power: Leveraging Physiological Priors for Self Supervised Representation Learning in Electrocardiographycited by 1
  34. 2025MEASURE: Multi-scale Minimal Sufficient Representation Learning for Domain Generalization in Sleep Stagingcited by 1
  35. 2026Empowering Time Series Analysis with Large-Scale Multimodal Pretrainingcited by 1
  36. 2026Orthogonalized Multimodal Contrastive Learning with Asymmetric Masking for Structured Representationscited by 1
  37. 2024HCL-MTSAD: Hierarchical Contrastive Consistency Learning for Accurate Detection of Industrial Multivariate Time Series Anomaliescited by 0
  38. 2024MSSDA: Multi-Sub-Source Adaptation for Diabetic Foot Neuropathy Recognitioncited by 0

50 most cited of 59 All 59 (JSON)