Unsupervised Scalable Representation Learning for Multivariate Time Series

01/30/2019
by   Jean-Yves Franceschi, et al.
0

Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn universal embeddings of time series. Unlike previous works, it is scalable with respect to their length and we demonstrate the quality, transferability and practicability of the learned representations with thorough experiments and comparisons. To this end, we combine an encoder based on causal dilated convolutions with a triplet loss employing time-based negative sampling, obtaining general-purpose representations for variable length and multivariate time series.

READ FULL TEXT
research
11/20/2019

Discovering Subdimensional Motifs of Different Lengths in Large-Scale Multivariate Time Series

Detecting repeating patterns of different lengths in time series, also c...
research
10/04/2020

TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series

Multivariate time series (MTS) data are becoming increasingly ubiquitous...
research
11/29/2018

Recurrent Deep Divergence-based Clustering for simultaneous feature learning and clustering of variable length time series

The task of clustering unlabeled time series and sequences entails a par...
research
02/12/2017

Similarity Preserving Representation Learning for Time Series Analysis

A considerable amount of machine learning algorithms take instance-featu...
research
08/06/2022

AUTOSHAPE: An Autoencoder-Shapelet Approach for Time Series Clustering

Time series shapelets are discriminative subsequences that have been rec...
research
10/10/2019

Graph Spectral Embedding for Parsimonious Transmission of Multivariate Time Series

We propose a graph spectral representation of time series data that 1) i...
research
02/10/2020

Representation Learning on Variable Length and Incomplete Wearable-Sensory Time Series

The prevalence of wearable sensors (e.g., smart wristband) is enabling a...

Please sign up or login with your details

Forgot password? Click here to reset