SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series
This work addresses the challenge of interpretability in unsupervised learning for high-rate time series, which is incremental as it builds on existing contrastive learning and self-organizing map techniques.
The paper tackles the problem of interpreting high-dimensional, high-rate time series by proposing SOM-CPC, a model that visualizes data in an organized 2D manifold while preserving higher-dimensional information. It shows that SOM-CPC outperforms strong baselines on synthetic and real-life data, including physiological data and audio recordings.
Continuous monitoring with an ever-increasing number of sensors has become ubiquitous across many application domains. However, acquired time series are typically high-dimensional and difficult to interpret. Expressive deep learning (DL) models have gained popularity for dimensionality reduction, but the resulting latent space often remains difficult to interpret. In this work we propose SOM-CPC, a model that visualizes data in an organized 2D manifold, while preserving higher-dimensional information. We address a largely unexplored and challenging set of scenarios comprising high-rate time series, and show on both synthetic and real-life data (physiological data and audio recordings) that SOM-CPC outperforms strong baselines like DL-based feature extraction, followed by conventional dimensionality reduction techniques, and models that jointly optimize a DL model and a Self-Organizing Map (SOM). SOM-CPC has great potential to acquire a better understanding of latent patterns in high-rate data streams.