Transfer learning for time series classification

Fawaz, Hassan Ismail; Forestier, Germain; Weber, Jonathan; Idoumghar, Lhassane; Müller, Pierre-Alain

doi:10.1109/bigdata.2018.8621990

Cited by 152 publications

(55 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…13 It is widely used in machine translation, [14][15][16] anomaly detection, [17][18][19] and time series classification. [20][21][22] At the same time, it is also very suitable for time series prediction as it processes backward and forward correlations based on memory characteristics. 23,24 However, such algorithms can only process historical data over short periods to make predictions, and have difficulty capturing their long-term dependencies.…”

Section: Introductionmentioning

confidence: 99%

A dual‐stage attention‐based Conv‐LSTM network for spatio‐temporal correlation and multivariate time series prediction

et al. 2021

View full text Add to dashboard Cite

Multivariate time series (MTS) prediction aims at predicting future time series by extracting multiple forms of dependencies of past time series. Traditional prediction methods and deep learning‐based prediction methods focus on extracting the dynamic relationships of certain aspects of MTS, especially the temporal characteristics, often neglecting the spatial and temporal dynamic correlations of MTS. Inspired by convolution neural network (CNN) and attention mechanism, this paper proposes a convolution LSTM network model based on MTS prediction with two‐stage attention. Specifically, we first propose a new MTS preprocessing method to perform convolution operations better. Then convolution layer extracts spatial correlation of MTS and LSTM model extracts temporal correlation. It is worth mentioning that the combination of attention mechanism and LSTM can effectively solve the problem of insufficient time dependency in MTS prediction. In addition, dual‐stage attention mechanism can effectively eliminate irrelevant information, select the relevant exogenous sequence, give it higher weight, and increase the past value of the target sequence to further eliminate irrelevant information. Finally, the MTS spatio‐temporal correlation is extracted to improve the prediction accuracy, and the model is interpreted. Experimental results show that the model has broad application prospects. Experiments based on typical datasets of finance, environment, and energy determine the optimal window size and hidden size of the prediction, and demonstrate that the model achieves the state‐of‐the‐art effect compared to the other four deep learning models. On top of that, the model is not only suitable for single‐step prediction of MTS, but also suitable for multistep prediction of time step in a certain range.

show abstract

Section: Introductionmentioning

confidence: 99%

A dual‐stage attention‐based Conv‐LSTM network for spatio‐temporal correlation and multivariate time series prediction

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, it is well-known that DNNs are prone to overfitting, especially when access to a large labeled training dataset is not available. [10,18].…”

Section: Introductionmentioning

confidence: 99%

Meta-Learning for Few-Shot Time Series Classification

Narwariya¹,

Malhotra²,

Vig³

et al. 2020

Proceedings of the 7th ACM IKDD CoDS and 25th COMAD

View full text Add to dashboard Cite

Deep neural networks (DNNs) have achieved state-of-the-art results on time series classification (TSC) tasks. In this work, we focus on leveraging DNNs in the often-encountered practical scenario where access to labeled training data is difficult, and where DNNs would be prone to overfitting. We leverage recent advancements in gradientbased meta-learning, and propose an approach to train a residual neural network with convolutional layers as a meta-learning agent for few-shot TSC. The network is trained on a diverse set of fewshot tasks sampled from various domains (e.g. healthcare, activity recognition, etc.) such that it can solve a target task from another domain using only a small number of training samples from the target task. Most existing meta-learning approaches are limited in practice as they assume a fixed number of target classes across tasks. We overcome this limitation in order to train a common agent across domains with each domain having different number of target classes, we utilize a triplet-loss based learning procedure that does not require any constraints to be enforced on the number of classes for the few-shot TSC tasks. To the best of our knowledge, we are the first to use meta-learning based pre-training for TSC. Our approach sets a new benchmark for few-shot TSC, outperforming several strong baselines on few-shot tasks sampled from 41 datasets in UCR TSC Archive. We observe that pre-training under the meta-learning paradigm allows the network to quickly adapt to new unseen tasks with small number of labeled instances.

show abstract

“…Therefore, we present our results on the UCR 2018 archive separated into two tables. The datasets already contained in the 2015 archive are compared with results from relevant publications and the new datasets are compared to the Dynamic Time Warping (DTW) published on the archives website 10,11 .…”

Section: Methodsmentioning

confidence: 99%

Timage – A Robust Time Series Classification Pipeline

Wenninger

Bayerl

Schmidt

et al. 2019

Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series

View full text Add to dashboard Cite

Time series are series of values ordered by time. This kind of data can be found in many real world settings. Classifying time series is a difficult task and an active area of research. This paper investigates the use of transfer learning in Deep Neural Networks and a 2D representation of time series known as Recurrence Plots. In order to utilize the research done in the area of image classification, where Deep Neural Networks have achieved very good results, we use a Residual Neural Networks architecture known as ResNet. As preprocessing of time series is a major part of every time series classification pipeline, the method proposed simplifies this step and requires only few parameters. For the first time we propose a method for multi time series classification: Training a single network to classify all datasets in the archive with one network. We are among the first to evaluate the method on the latest 2018 release of the UCR archive, a well established time series classification benchmarking dataset.

show abstract

Transfer learning for time series classification

Cited by 152 publications

References 26 publications

A dual‐stage attention‐based Conv‐LSTM network for spatio‐temporal correlation and multivariate time series prediction

A dual‐stage attention‐based Conv‐LSTM network for spatio‐temporal correlation and multivariate time series prediction

Meta-Learning for Few-Shot Time Series Classification

Timage – A Robust Time Series Classification Pipeline

Contact Info

Product

Resources

About