SimPer: Simple Self-Supervised Learning of Periodic Targets
This addresses the challenge of label scarcity in periodic data for domains such as healthcare and environmental sensing, offering a novel approach but with incremental improvements over existing SSL frameworks.
The paper tackles the problem of learning useful representations for periodic tasks with limited supervision, presenting SimPer, a self-supervised learning method that outperforms state-of-the-art SSL methods in real-world tasks like human behavior analysis and healthcare, achieving better data efficiency and robustness.
From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes. Due to their inherent label scarcity, learning useful representations for periodic tasks with limited or no supervision is of great benefit. Yet, existing self-supervised learning (SSL) methods overlook the intrinsic periodicity in data, and fail to learn representations that capture periodic or frequency attributes. In this paper, we present SimPer, a simple contrastive SSL regime for learning periodic information in data. To exploit the periodic inductive bias, SimPer introduces customized augmentations, feature similarity measures, and a generalized contrastive loss for learning efficient and robust periodic representations. Extensive experiments on common real-world tasks in human behavior analysis, environmental sensing, and healthcare domains verify the superior performance of SimPer compared to state-of-the-art SSL methods, highlighting its intriguing properties including better data efficiency, robustness to spurious correlations, and generalization to distribution shifts. Code and data are available at: https://github.com/YyzHarry/SimPer.