Deep Symbolic Representation Learning for Heterogeneous Time-series Classification

TL;DR

This paper introduces deep symbolic representation learning methods for classifying heterogeneous multivariate time-series data, effectively capturing complex temporal dependencies and variable heterogeneity in an end-to-end deep learning framework.

Contribution

It proposes three novel representation learning algorithms for symbolized sequences that enable end-to-end classification of heterogeneous time-series data, outperforming traditional methods.

Findings

Effective classification on three real-world datasets.

Outperforms existing approaches in handling heterogeneous variables.

Learned features are highly discriminative for event classification.

Abstract

In this paper, we consider the problem of event classification with multi-variate time series data consisting of heterogeneous (continuous and categorical) variables. The complex temporal dependencies between the variables combined with sparsity of the data makes the event classification problem particularly challenging. Most state-of-art approaches address this either by designing hand-engineered features or breaking up the problem over homogeneous variates. In this work, we propose and compare three representation learning algorithms over symbolized sequences which enables classification of heterogeneous time-series data using a deep architecture. The proposed representations are trained jointly along with the rest of the network architecture in an end-to-end fashion that makes the learned features discriminative for the given task. Experiments on three real-world datasets demonstrate the effectiveness of the proposed approaches.