Unsupervised Scalable Representation Learning for Multivariate Time Series

2019-01-30 · NeurIPS 2019 12 · Jean-Yves Franceschi, Aymeric Dieuleveut, Martin Jaggi

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 novel triplet loss employing time-based negative sampling, obtaining general-purpose representations for variable length and multivariate time series.

📄 PDF Abstract BibTeX arXiv:1901.10738

Code (1)

White-Link/UnsupervisedScalableRepresentationLearningTimeSeries 공식 구현 pytorch

Tasks

BIG-bench Machine Learning Representation LearningTime SeriesTime Series AnalysisTriplet

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

A Transformer-based Framework for Multivariate Time Series Representation Learning

2020-10-06 · George Zerveas, Srideepika Jayaraman, Dhaval Patel, Anuradha Bhamidipaty 외

In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially used for downstream tasks such as regre…

Computational Efficiency General Classification Imputation regression+6

Ymir: A Supervised Ensemble Framework for Multivariate Time Series Anomaly Detection

2021-12-09 · Zhanxiang Zhao

We proposed a multivariate time series anomaly detection frame-work Ymir, which leverages ensemble learning and supervisedlearning technology to efficiently learn and adapt to anomaliesin real-world system applications. …

Anomaly Detection Ensemble Learning Time Series Time Series Analysis+2

Unsupervised 4D LiDAR Moving Object Segmentation in Stationary Settings with Multivariate Occupancy Time Series

2022-12-30 · Thomas Kreutz, Max Mühlhäuser, Alejandro Sanchez Guinea

In this work, we address the problem of unsupervised moving object segmentation (MOS) in 4D LiDAR data recorded from a stationary sensor, where no ground truth annotations are involved. Deep learning-based state-of-the-a…

Clustering Semantic Segmentation Time Series Time Series Analysis+1

An Unsupervised Short- and Long-Term Mask Representation for Multivariate Time Series Anomaly Detection

2022-08-19 · Qiucheng Miao, Chuanfu Xu, Jun Zhan, Dong zhu 외

Anomaly detection of multivariate time series is meaningful for system behavior monitoring. This paper proposes an anomaly detection method based on unsupervised Short- and Long-term Mask Representation learning (SLMR). …

Anomaly Detection Representation Learning Time Series Time Series Analysis+1

GenAD: General Representations of Multivariate Time Series for Anomaly Detection

2021-01-01 · Xiaolei Hua, Su Wang, Lin Zhu, Dong Zhou 외

Anomaly Detection(AD) for multivariate time series is an active area in machine learning, with critical applications in Information Technology system management, Spacecraft Health monitoring, Multi-Robot Systems detectio…

Anomaly Detection Management Time Series Time Series Analysis+1