通过多视角对比学习提升医疗时序数据跨域适应能力
Multi-View Contrastive Learning for Robust Domain Adaptation in Medical Time Series Analysis
- 设计多视角对比学习框架，融合时间、动态与频域特征
- 在EEG/ECG/EMG数据上超越现有方法，提升跨域迁移性能
- 适合需要高鲁棒性的医疗AI系统部署场景
由于复杂的时序依赖和动态分布偏移，将机器学习模型应用于不同领域的医疗时序数据仍具挑战。现有方法多关注孤立特征表示，难以充分捕捉关键时序动态。本文提出一种新框架，利用多视角对比学习整合时间模式、导数动态和频域特征。采用独立编码器与分层融合机制，学习具有特征不变性且保持时序一致性的可迁移表示。在多种医疗数据集（包括脑电图EEG、心电图ECG和肌电图EMG）上的大量实验表明，该方法在迁移学习任务中显著优于现有最优方法。本框架提升了模型的鲁棒性和泛化能力，为在多样化医疗环境中部署可靠AI系统提供了可行路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。