A review on distance based time series classification
Time series classification is an increasing research topic due to the vast amount of time
series data that is being created over a wide variety of fields. The particularity of the data …
series data that is being created over a wide variety of fields. The particularity of the data …
Ts2vec: Towards universal representation of time series
This paper presents TS2Vec, a universal framework for learning representations of time
series in an arbitrary semantic level. Unlike existing methods, TS2Vec performs contrastive …
series in an arbitrary semantic level. Unlike existing methods, TS2Vec performs contrastive …
Unsupervised scalable representation learning for multivariate time series
JY Franceschi, A Dieuleveut… - Advances in neural …, 2019 - proceedings.neurips.cc
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 …
highly variable lengths and sparse labeling in practice. In this paper, we tackle this …
Timemae: Self-supervised representations of time series with decoupled masked autoencoders
Enhancing the expressive capacity of deep learning-based time series models with self-
supervised pre-training has become ever-increasingly prevalent in time series classification …
supervised pre-training has become ever-increasingly prevalent in time series classification …
Word mover's embedding: From word2vec to document embedding
While the celebrated Word2Vec technique yields semantically rich representations for
individual words, there has been relatively less success in extending to generate …
individual words, there has been relatively less success in extending to generate …
Modeling temporal patterns with dilated convolutions for time-series forecasting
Time-series forecasting is an important problem across a wide range of domains. Designing
accurate and prompt forecasting algorithms is a non-trivial task, as temporal data that arise …
accurate and prompt forecasting algorithms is a non-trivial task, as temporal data that arise …
Debunking four long-standing misconceptions of time-series distance measures
Distance measures are core building blocks in time-series analysis and the subject of active
research for decades. Unfortunately, the most detailed experimental study in this area is …
research for decades. Unfortunately, the most detailed experimental study in this area is …
Towards similarity-aware time-series classification
We study time-series classification (TSC), a fundamental task of time-series data mining.
Prior work has approached TSC from two major directions:(1) similarity-based methods that …
Prior work has approached TSC from two major directions:(1) similarity-based methods that …
Grail: efficient time-series representation learning
J Paparrizos, MJ Franklin - Proceedings of the VLDB Endowment, 2019 - dl.acm.org
The analysis of time series is becoming increasingly prevalent across scientific disciplines
and industrial applications. The effectiveness and the scalability of time-series mining …
and industrial applications. The effectiveness and the scalability of time-series mining …
Smate: Semi-supervised spatio-temporal representation learning on multivariate time series
Learning from Multivariate Time Series (MTS) has attracted widespread attention in recent
years. In particular, label shortage is a real challenge for the classification task on MTS …
years. In particular, label shortage is a real challenge for the classification task on MTS …