# SOM-VAE: Interpretable Discrete Representation Learning on Time Series

arXiv: https://arxiv.org/abs/1806.02199 · HTML: https://mlsanity.com/paper/1806.02199/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2018.

## Built on by (most cited first, 30 of 60)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Priors in Bayesian Deep Learning: A Review](https://mlsanity.com/paper/2105.06868/) (2021)
- [Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement](https://mlsanity.com/paper/2301.03028/) (2023)
- [EEGFormer: Towards Transferable and Interpretable Large-Scale EEG Foundation Model](https://mlsanity.com/paper/2401.10278/) (2024)
- [Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation](https://mlsanity.com/paper/2112.01799/) (2021)
- [On the Challenges and Opportunities in Generative AI](https://mlsanity.com/paper/2403.00025/) (2024)
- [TSGBench: Time Series Generation Benchmark](https://mlsanity.com/paper/2309.03755/) (2023)
- [Variable-rate discrete representation learning](https://mlsanity.com/paper/2103.06089/) (2021)
- [Generative learning for nonlinear dynamics](https://mlsanity.com/paper/2311.04128/) (2023)
- [T-Rep: Representation Learning for Time Series using Time-Embeddings](https://mlsanity.com/paper/2310.04486/) (2023)
- [Decoupling Local and Global Representations of Time Series](https://mlsanity.com/paper/2202.02262/) (2022)
- [Learning Conditional Variational Autoencoders with Missing Covariates](https://mlsanity.com/paper/2203.01218/) (2022)
- [Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts](https://mlsanity.com/paper/2402.05970/) (2024)
- [Learning Disentangled Representations for Time Series](https://mlsanity.com/paper/2105.08179/) (2021)
- [Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective](https://mlsanity.com/paper/2301.11535/) (2023)
- [Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2209.00654/) (2022)
- [Learning Differential Operators for Interpretable Time Series Modeling](https://mlsanity.com/paper/2209.01491/) (2022)
- [Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models](https://mlsanity.com/paper/2110.14182/) (2021)
- [eVAE: Evolutionary Variational Autoencoder](https://mlsanity.com/paper/2301.00011/) (2023)
- [Coupled Variational Autoencoder](https://mlsanity.com/paper/2306.02565/) (2023)
- [Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidance](https://mlsanity.com/paper/2403.13850/) (2024)
- [SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series](https://mlsanity.com/paper/2205.15875/) (2022)
- [Learning from Polar Representation: An Extreme-Adaptive Model for Long-Term Time Series Forecasting](https://mlsanity.com/paper/2312.08763/) (2023)
- [Mixture-of-Experts Variational Autoencoder for Clustering and Generating from Similarity-Based Representations on Single Cell Data](https://mlsanity.com/paper/1910.07763/) (2019)
- [VQ-AR: Vector Quantized Autoregressive Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2205.15894/) (2022)
- [Symmetrical SyncMap for Imbalanced General Chunking Problems](https://mlsanity.com/paper/2310.10045/) (2023)
- [Behavior Estimation from Multi-Source Data for Offline Reinforcement Learning](https://mlsanity.com/paper/2211.16078/) (2022)
- [LSOR: Longitudinally-Consistent Self-Organized Representation Learning](https://mlsanity.com/paper/2310.00213/) (2023)
- [Position Paper on Materials Design -- A Modern Approach](https://mlsanity.com/paper/2312.10996/) (2023)
- [Symbolic Autoencoding for Self-Supervised Sequence Learning](https://mlsanity.com/paper/2402.10575/) (2024)

## Abstract (arXiv)

High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most representation learning algorithms for time series data are difficult to interpret. This is due to non-intuitive mappings from data features to salient properties of the representation and non-smoothness over time. To address this problem, we propose a new representation learning framework building on ideas from interpretable discrete dimensionality reduction and deep generative modeling. This framework allows us to learn discrete representations of time series, which give rise to smooth and interpretable embeddings with superior clustering performance. We introduce a new way to overcome the non-differentiability in discrete representation learning and present a gradient-based version of the traditional self-organizing map algorithm that is more performant than the original. Furthermore, to allow for a probabilistic interpretation of our method, we integrate a Markov model in the representation space. This model uncovers the temporal transition structure, improves clustering performance even further and provides additional explanatory insights as well as a natural representation of uncertainty. We evaluate our model in terms of clustering performance and interpretability on static (Fashion-)MNIST data, a time series of linearly interpolated (Fashion-)MNIST images, a chaotic Lorenz attractor system with two macro states, as well as on a challenging real world medical time series application on the eICU data set. Our learned representations compare favorably with competitor methods and facilitate downstream tasks on the real world data.