# Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization

arXiv: https://arxiv.org/abs/1610.07258 · HTML: https://mlsanity.com/paper/1610.07258/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2016.

## Built on by (most cited first, 4 of 4)

- [Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction](https://mlsanity.com/paper/2409.00265/) (2024)
- [Unsupervised Representation Learning for Time Series: A Review](https://mlsanity.com/paper/2308.01578/) (2023)
- [Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Mask](https://mlsanity.com/paper/2405.05959/) (2024)
- [XAI Methods for Neural Time Series Classification: A Brief Review](https://mlsanity.com/paper/2108.08009/) (2021)

## Abstract (arXiv)

We propose a new model based on the deconvolutional networks and SAX discretization to learn the representation for multivariate time series. Deconvolutional networks fully exploit the advantage the powerful expressiveness of deep neural networks in the manner of unsupervised learning. We design a network structure specifically to capture the cross-channel correlation with deconvolution, forcing the pooling operation to perform the dimension reduction along each position in the individual channel. Discretization based on Symbolic Aggregate Approximation is applied on the feature vectors to further extract the bag of features. We show how this representation and bag of features helps on classification. A full comparison with the sequence distance based approach is provided to demonstrate the effectiveness of our approach on the standard datasets. We further build the Markov matrix from the discretized representation from the deconvolution to visualize the time series as complex networks, which show more class-specific statistical properties and clear structures with respect to different labels.