想用少量标注数据做心电图分析？这篇论文提出的ER-JEPA用18万条无标注ECG预训练，在ST-MEM基准上跑出SOTA，计算量还比同类方法小。
本文提出Event Reconstruction Joint-Embedding Predictive Architecture (ER-JEPA)，一种用于多变量时间序列的轻量级自监督学习框架。其两阶段层次结构受心脏病专家诊断方法启发，先构建每个时间间隔的表示，再将表示作为单变量时间序列处理，层次整合两个JEPA和Vision Transformer (ViT) 骨干。在约18万条10秒12导联ECG数据上预训练后，模型在ST-MEM基准上达到下游任务SOTA，且计算快速、资源占用极低。
A Lightweight Self-Supervised Learning Framework for Multivariate Time Series using Hierarchical-JEPA on ECG Data
Data analysis in the medical domain often encounters scenarios involving a limited target dataset and a large, unannotated dataset with a general distribution. Under such circumstances, self-supervised learning (SSL) methods are highly effective for utilizing large datasets, making them a popular choice for electrocardiogram (ECG) analysis. This work presents the Event Reconstruction Joint-Embedding Predictive Architecture (ER-JEPA), a lightweight SSL framework for multivariate time series, whose name and two-fold hierarchical structure are inspired by the diagnostic approach of cardiologists. At its core, ER-JEPA features: (1) a two-stage structure that constructs representations for each time interval and subsequently processes these representations as a univariate time series, (2) the hierarchical integration of two Joint-Embedding Predictive Architectures (JEPAs), and (3) a Vision Transformer (ViT) backbone. The structural concatenation of two JEPAs categorizes the model as a Hierarchical JEPA (H-JEPA), designed to encode multiple levels of abstract representations for enhanced prediction on complex tasks. This study reports a successful application of H-JEPA to 12-lead ECG data as a multivariate time series alongside an analysis of the sensitivity of hierarchical representation during the pretraining stage. Pretrained on approximately 180,000 10-second recordings, the model achieves state-of-the-art downstream performance on the ST-MEM benchmark, with rapid computation and minimal resource usage.