CE-SSL: Computation-Efficient Semi-Supervised Learning for ECG-based Cardiovascular Diseases Detection

TL;DR

This paper introduces CE-SSL, a semi-supervised learning framework that enhances ECG-based cardiovascular disease detection by improving computational efficiency and robustness, especially with limited labeled data.

Contribution

The paper proposes a novel computation-efficient semi-supervised learning paradigm with a random-deactivation technique and one-shot rank allocation for robust adaptation of pre-trained models on ECG data.

Findings

Outperforms state-of-the-art methods in multi-label CVD detection.

Reduces GPU usage, training time, and parameter storage.

Demonstrates robustness and efficiency on four datasets.

Abstract

The label scarcity problem is the main challenge that hinders the wide application of deep learning systems in automatic cardiovascular diseases (CVDs) detection using electrocardiography (ECG). Tuning pre-trained models alleviates this problem by transferring knowledge learned from large datasets to downstream small datasets. However, bottlenecks in computational efficiency and detection performance limit its clinical applications. It is difficult to improve the detection performance without significantly sacrificing the computational efficiency during model training. Here, we propose a computation-efficient semi-supervised learning paradigm (CE-SSL) for robust and computation-efficient CVDs detection using ECG. It enables a robust adaptation of pre-trained models on downstream datasets with limited supervision and high computational efficiency. First, a random-deactivation technique is developed to achieve robust and fast low-rank adaptation of pre-trained weights. Subsequently, we propose a one-shot rank allocation module to determine the optimal ranks for the update matrices of the pre-trained weights. Finally, a lightweight semi-supervised learning pipeline is introduced to enhance model performance by leveraging labeled and unlabeled data with high computational efficiency. Extensive experiments on four downstream datasets demonstrate that CE-SSL not only outperforms the state-of-the-art methods in multi-label CVDs detection but also consumes fewer GPU footprints, training time, and parameter storage space. As such, this paradigm provides an effective solution for achieving high computational efficiency and robust detection performance in the clinical applications of pre-trained models under limited supervision. Code and Supplementary Materials are available at https://github.com/KAZABANA/CE-SSL