SigTime: Learning and Visually Explaining Time Series Signatures
This work addresses challenges in time series pattern discovery for domains like biomedical research, offering improved interpretability and computational efficiency, though it appears incremental as it builds on existing Transformer and shapelet methods.
The paper tackles the problem of understanding and distinguishing temporal patterns in time series data by introducing a novel learning framework that jointly trains Transformer models with shapelet-based and feature-engineered representations, achieving interpretable signatures for classification and demonstrating effectiveness on nine datasets including clinical applications.
Understanding and distinguishing temporal patterns in time series data is essential for scientific discovery and decision-making. For example, in biomedical research, uncovering meaningful patterns in physiological signals can improve diagnosis, risk assessment, and patient outcomes. However, existing methods for time series pattern discovery face major challenges, including high computational complexity, limited interpretability, and difficulty in capturing meaningful temporal structures. To address these gaps, we introduce a novel learning framework that jointly trains two Transformer models using complementary time series representations: shapelet-based representations to capture localized temporal structures and traditional feature engineering to encode statistical properties. The learned shapelets serve as interpretable signatures that differentiate time series across classification labels. Additionally, we develop a visual analytics system -- SigTIme -- with coordinated views to facilitate exploration of time series signatures from multiple perspectives, aiding in useful insights generation. We quantitatively evaluate our learning framework on eight publicly available datasets and one proprietary clinical dataset. Additionally, we demonstrate the effectiveness of our system through two usage scenarios along with the domain experts: one involving public ECG data and the other focused on preterm labor analysis.