Deep Temporal Clustering : Fully Unsupervised Learning of Time-Domain Features

TL;DR

Deep Temporal Clustering (DTC) is a fully unsupervised, end-to-end algorithm that combines dimensionality reduction and temporal clustering using autoencoders and customizable similarity metrics, outperforming traditional methods across diverse time series data.

Contribution

The paper introduces DTC, a novel unsupervised framework that integrates temporal dimensionality reduction and clustering into a single end-to-end model with customizable similarity metrics.

Findings

DTC outperforms traditional clustering methods on diverse datasets.

The method effectively visualizes learned temporal features.

Customizable similarity metrics enhance clustering flexibility.

Abstract

Unsupervised learning of time series data, also known as temporal clustering, is a challenging problem in machine learning. Here we propose a novel algorithm, Deep Temporal Clustering (DTC), to naturally integrate dimensionality reduction and temporal clustering into a single end-to-end learning framework, fully unsupervised. The algorithm utilizes an autoencoder for temporal dimensionality reduction and a novel temporal clustering layer for cluster assignment. Then it jointly optimizes the clustering objective and the dimensionality reduction objec tive. Based on requirement and application, the temporal clustering layer can be customized with any temporal similarity metric. Several similarity metrics and state-of-the-art algorithms are considered and compared. To gain insight into temporal features that the network has learned for its clustering, we apply a visualization method that generates a region of interest heatmap for the time series. The viability of the algorithm is demonstrated using time series data from diverse domains, ranging from earthquakes to spacecraft sensor data. In each case, we show that the proposed algorithm outperforms traditional methods. The superior performance is attributed to the fully integrated temporal dimensionality reduction and clustering criterion.