mlsanityData to 14 Oct 2026

SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series

arXiv 2205.15875 ↗First posted 31 May 2022cs.LG cs.NEcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 23 of its 39 references that are in the map. First posted on arXiv 31 May 2022.

Builds on

23 of 39 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2017Neural Discrete Representation Learningcited by 4,712
  6. 2013Auto-Encoding Variational Bayescited by 4,053
  7. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  8. 2016The Mythos of Model Interpretabilitycited by 721
  9. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  10. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 282
  11. 2016Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clusteringcited by 237
  12. 2021Contrastive Learning Inverts the Data Generating Processcited by 221
11 more
  1. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 144
  2. 2017Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networkscited by 131
  3. 2018SOM-VAE: Interpretable Discrete Representation Learning on Time Seriescited by 60
  4. 2017A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time seriescited by 58
  5. 2018Deep Temporal Clustering : Fully Unsupervised Learning of Time-Domain Featurescited by 37
  6. 2020Temporal Phenotyping using Deep Predictive Clustering of Disease Progressioncited by 26
  7. 2019Adversarial Deep Embedded Clustering: on a better trade-off between Feature Randomness and Feature Driftcited by 12
  8. 2020Improving Self-Organizing Maps with Unsupervised Feature Extractioncited by 5
  9. 2020A Survey and Implementation of Performance Metrics for Self-Organized Mapscited by 5
  10. 2018Deep Neural Mapscited by 2
  11. 2020Deep Categorization with Semi-Supervised Self-Organizing Mapscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 2.

4 papers.

  1. 2023Generative learning for nonlinear dynamicscited by 22
  2. 2023Cortex Inspired Learning to Recover Damaged Signal Modality with ReD-SOM Modelcited by 0
  3. 2025Contrastive Representation Learning Helps Cross-institutional Knowledge Transfer: A Study in Pediatric Ventilation Managementcited by 0
  4. 2025Simple Self Organizing Map with Vision Transformerscited by 0