Learning Beyond Similarities: Incorporating Dissimilarities between Positive Pairs in Self-Supervised Time Series Learning
This work addresses the challenge of capturing dynamic characteristics in time series data for medical applications like ECG analysis, offering an incremental advance in SSL methods.
The paper tackled the problem of self-supervised learning for time series focusing too much on similarities, which overlooks dynamic attributes critical for cardiovascular disease modeling. By introducing DEBS to incorporate dissimilarities among positive pairs, it achieved a +10% improvement in Atrial Fibrillation detection accuracy across diverse subjects.
By identifying similarities between successive inputs, Self-Supervised Learning (SSL) methods for time series analysis have demonstrated their effectiveness in encoding the inherent static characteristics of temporal data. However, an exclusive emphasis on similarities might result in representations that overlook the dynamic attributes critical for modeling cardiovascular diseases within a confined subject cohort. Introducing Distilled Encoding Beyond Similarities (DEBS), this paper pioneers an SSL approach that transcends mere similarities by integrating dissimilarities among positive pairs. The framework is applied to electrocardiogram (ECG) signals, leading to a notable enhancement of +10\% in the detection accuracy of Atrial Fibrillation (AFib) across diverse subjects. DEBS underscores the potential of attaining a more refined representation by encoding the dynamic characteristics of time series data, tapping into dissimilarities during the optimization process. Broadly, the strategy delineated in this study holds the promise of unearthing novel avenues for advancing SSL methodologies tailored to temporal data.