Multi-View Contrastive Learning for Robust Domain Adaptation in Medical Time Series Analysis

TL;DR

This paper introduces a multi-view contrastive learning framework that enhances domain adaptation in medical time series analysis by capturing complex temporal, dynamic, and frequency features, leading to improved transferability across diverse healthcare datasets.

Contribution

The proposed method uniquely integrates multiple feature views with independent encoders and hierarchical fusion, advancing robust domain adaptation in medical time series analysis.

Findings

Outperforms state-of-the-art transfer learning methods on EEG, ECG, and EMG datasets.

Significantly improves robustness and generalizability of models across domains.

Demonstrates practical applicability for deploying reliable AI in healthcare settings.

Abstract

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.