Symbol-Temporal Consistency Self-supervised Learning for Robust Time Series Classification

2025/09/24 by Garcia, Kevin, Garza, Cassandra, Berry, Brooklyn +1
#FOS: Computer and information sciences #I.2.6 #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2509.19654

Abstract

The surge in the significance of time series in digital health domains necessitates advanced methodologies for extracting meaningful patterns and representations. Self-supervised contrastive learning has emerged as a promising approach for learning directly from raw data. However, time series data in digital health is known to be highly noisy, inherently involves concept drifting, and poses a challenge for training a generalizable deep learning model. In this paper, we specifically focus on data distribution shift caused by different human behaviors and propose a self-supervised learning framework that is aware of the bag-of-symbol representation. The bag-of-symbol representation is known for its insensitivity to data warping, location shifts, and noise existed in time series data, making it potentially pivotal in guiding deep learning to acquire a representation resistant to such data shifting. We demonstrate that the proposed method can achieve significantly better performance where significant data shifting exists.

Citations

• SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
• Deep learning in ECG diagnosis: A review
• Time-Series Representation Learning via Temporal and Contextual Contrasting
• TS2Vec: Towards Universal Representation of Time Series
• Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding
• Adjusting for Autocorrelated Errors in Neural Networks for Time Series
• Bootstrap your own latent: A new approach to self-supervised Learning
• CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients
• A Simple Framework for Contrastive Learning of Visual Representations

Related

• Multi-Task Self-Supervised Time-Series Representation Learning
• Self-Supervised Learning for Time Series: Contrastive or Generative?
• Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder
• Time Series Representation Learning with Supervised Contrastive Temporal Transformer
• Self-Distilled Representation Learning for Time Series