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

arXiv: https://arxiv.org/abs/2310.14017 · HTML: https://mlsanity.com/paper/2310.14017/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 53 references that are in the map.
- First posted on arXiv 21 Oct 2023.

## Builds on (most cited first, 25 of 25)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients](https://mlsanity.com/paper/2005.13249/) (2020)
- [LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks](https://mlsanity.com/paper/2206.06565/) (2022)
- [Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion](https://mlsanity.com/paper/2202.04770/) (2022)
- [Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis](https://mlsanity.com/paper/2104.08336/) (2021)
- [Exploring Contrastive Learning in Human Activity Recognition for Healthcare](https://mlsanity.com/paper/2011.11542/) (2020)
- [Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series](https://mlsanity.com/paper/2203.09270/) (2022)
- [End-to-End Human-Gaze-Target Detection with Transformers](https://mlsanity.com/paper/2203.10433/) (2022)
- [Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signals](https://mlsanity.com/paper/2109.08908/) (2021)
- [Neighborhood Contrastive Learning Applied to Online Patient Monitoring](https://mlsanity.com/paper/2106.05142/) (2021)
- [ManyDG: Many-domain Generalization for Healthcare Applications](https://mlsanity.com/paper/2301.08834/) (2023)
- [Utilizing Expert Features for Contrastive Learning of Time-Series Representations](https://mlsanity.com/paper/2206.11517/) (2022)
- [Discovery of Single Independent Latent Variable](https://mlsanity.com/paper/2110.05887/) (2021)
- [Medusa: Universal Feature Learning via Attentional Multitasking](https://mlsanity.com/paper/2204.05698/) (2022)
- [Contrastive Graph Few-Shot Learning](https://mlsanity.com/paper/2210.00084/) (2022)

## Built on by (most cited first, 30 of 59)

- [Timer: Generative Pre-trained Transformers Are Large Time Series Models](https://mlsanity.com/paper/2402.02368/) (2024)
- [UniTS: A Unified Multi-Task Time Series Model](https://mlsanity.com/paper/2403.00131/) (2024)
- [Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification](https://mlsanity.com/paper/2405.19363/) (2024)
- [Towards Neural Scaling Laws for Time Series Foundation Models](https://mlsanity.com/paper/2410.12360/) (2024)
- [Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer](https://mlsanity.com/paper/2405.17478/) (2024)
- [Universal Time-Series Representation Learning: A Survey](https://mlsanity.com/paper/2401.03717/) (2024)
- [LightGTS: A Lightweight General Time Series Forecasting Model](https://mlsanity.com/paper/2506.06005/) (2025)
- [Aurora: Towards Universal Generative Multimodal Time Series Forecasting](https://mlsanity.com/paper/2509.22295/) (2025)
- [CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2505.23116/) (2025)
- [TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling](https://mlsanity.com/paper/2402.02475/) (2024)
- [Medical Multimodal Foundation Models in Clinical Diagnosis and Treatment: Applications, Challenges, and Future Directions](https://mlsanity.com/paper/2412.02621/) (2024)
- [Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models](https://mlsanity.com/paper/2410.09385/) (2024)
- [An Open and Large-Scale Dataset for Multi-Modal Climate Change-aware Crop Yield Predictions](https://mlsanity.com/paper/2406.06081/) (2024)
- [MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning](https://mlsanity.com/paper/2406.06620/) (2024)
- [Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning](https://mlsanity.com/paper/2412.20790/) (2024)
- [LEAD: An EEG Foundation Model for Alzheimer's Disease Detection](https://mlsanity.com/paper/2502.01678/) (2025)
- [MedGNN: Towards Multi-resolution Spatiotemporal Graph Learning for Medical Time Series Classification](https://mlsanity.com/paper/2502.04515/) (2025)
- [CREMA: A Contrastive Regularized Masked Autoencoder for Robust ECG Diagnostics across Clinical Domains](https://mlsanity.com/paper/2407.07110/) (2024)
- [ADAPT: Multimodal Learning for Detecting Physiological Changes under Missing Modalities](https://mlsanity.com/paper/2407.03836/) (2024)
- [Toward Robust Early Detection of Alzheimer's Disease via an Integrated Multimodal Learning Approach](https://mlsanity.com/paper/2408.16343/) (2024)
- [Repurposing Foundation Model for Generalizable Medical Time Series Classification](https://mlsanity.com/paper/2410.03794/) (2024)
- [UniCL: A Universal Contrastive Learning Framework for Large Time Series Models](https://mlsanity.com/paper/2405.10597/) (2024)
- [Guidelines for Augmentation Selection in Contrastive Learning for Time Series Classification](https://mlsanity.com/paper/2407.09336/) (2024)
- [EMIT- Event-Based Masked Auto Encoding for Irregular Time Series](https://mlsanity.com/paper/2409.16554/) (2024)
- [Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series](https://mlsanity.com/paper/2602.18473/) (2026)
- [Fuzzy Cluster-Aware Contrastive Clustering for Time Series](https://mlsanity.com/paper/2503.22211/) (2025)
- [Multi-View Contrastive Learning for Robust Domain Adaptation in Medical Time Series Analysis](https://mlsanity.com/paper/2506.22393/) (2025)
- [Scalable Transformer for High Dimensional Multivariate Time Series Forecasting](https://mlsanity.com/paper/2408.04245/) (2024)
- [FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting](https://mlsanity.com/paper/2512.14253/) (2025)
- [Empowering Time Series Analysis with Large-Scale Multimodal Pretraining](https://mlsanity.com/paper/2602.05646/) (2026)

## 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.