Multi-View Contrastive Learning for Robust Domain Adaptation in Medical Time Series Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912595113410560 |
|---|---|
| author | Oh, YongKyung Bui, Alex |
| author_facet | Oh, YongKyung Bui, Alex |
| contents | Adapting machine learning models to medical time series across different domains remains a challenge due to complex temporal dependencies and dynamic distribution shifts. Current approaches often focus on isolated feature representations, limiting their ability to fully capture the intricate temporal dynamics necessary for robust domain adaptation. In this work, we propose a novel framework leveraging multi-view contrastive learning to integrate temporal patterns, derivative-based dynamics, and frequency-domain features. Our method employs independent encoders and a hierarchical fusion mechanism to learn feature-invariant representations that are transferable across domains while preserving temporal coherence. Extensive experiments on diverse medical datasets, including electroencephalogram (EEG), electrocardiogram (ECG), and electromyography (EMG) demonstrate that our approach significantly outperforms state-of-the-art methods in transfer learning tasks. By advancing the robustness and generalizability of machine learning models, our framework offers a practical pathway for deploying reliable AI systems in diverse healthcare settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22393 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-View Contrastive Learning for Robust Domain Adaptation in Medical Time Series Analysis Oh, YongKyung Bui, Alex Machine Learning Artificial Intelligence Adapting machine learning models to medical time series across different domains remains a challenge due to complex temporal dependencies and dynamic distribution shifts. Current approaches often focus on isolated feature representations, limiting their ability to fully capture the intricate temporal dynamics necessary for robust domain adaptation. In this work, we propose a novel framework leveraging multi-view contrastive learning to integrate temporal patterns, derivative-based dynamics, and frequency-domain features. Our method employs independent encoders and a hierarchical fusion mechanism to learn feature-invariant representations that are transferable across domains while preserving temporal coherence. Extensive experiments on diverse medical datasets, including electroencephalogram (EEG), electrocardiogram (ECG), and electromyography (EMG) demonstrate that our approach significantly outperforms state-of-the-art methods in transfer learning tasks. By advancing the robustness and generalizability of machine learning models, our framework offers a practical pathway for deploying reliable AI systems in diverse healthcare settings. |
| title | Multi-View Contrastive Learning for Robust Domain Adaptation in Medical Time Series Analysis |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.22393 |