Multivariate Temporal Autoencoder for Predictive Reconstruction of Deep Sequences

TL;DR

This paper introduces MvTAe, a multi-branch deep neural network that models latent representations of multivariate time series data for improved predictive reconstruction of complex sequences.

Contribution

It presents a novel multi-branch autoencoder architecture that captures interactions among multiple dimensions in temporal data for sequence prediction.

Findings

Effective modeling of multi-dimensional temporal data.

Improved sequence reconstruction accuracy.

Ability to handle complex latent interactions.

Abstract

Time series sequence prediction and modelling has proven to be a challenging endeavor in real world datasets. Two key issues are the multi-dimensionality of data and the interaction of independent dimensions forming a latent output signal, as well as the representation of multi-dimensional temporal data inside of a predictive model. This paper proposes a multi-branch deep neural network approach to tackling the aforementioned problems by modelling a latent state vector representation of data windows through the use of a recurrent autoencoder branch and subsequently feeding the trained latent vector representation into a predictor branch of the model. This model is henceforth referred to as Multivariate Temporal Autoencoder (MvTAe). The framework in this paper utilizes a synthetic multivariate temporal dataset which contains dimensions that combine to create a hidden output target.