DSTP-RNN: a dual-stage two-phase attention-based recurrent neural networks for long-term and multivariate time series prediction

@article{Liu2020DSTPRNNAD,
  title={DSTP-RNN: a dual-stage two-phase attention-based recurrent neural networks for long-term and multivariate time series prediction},
  author={Yeqi Liu and Chuanyang Gong and Ling Yang and Yingyi Chen},
  journal={ArXiv},
  year={2020},
  volume={abs/1904.07464}
}
Long-term prediction of multivariate time series is still an important but challenging problem. The key to solve this problem is to capture the spatial correlations at the same time, the spatio-temporal relationships at different times and the long-term dependence of the temporal relationships between different series. Attention-based recurrent neural networks (RNN) can effectively represent the dynamic spatio-temporal relationships between exogenous series and target series, but it only… Expand
CDA-LSTM: an evolutionary convolution-based dual-attention LSTM for univariate time series prediction
  • Xiaoquan Chu, Haibin Jin, Yue Li, Jianying Feng, Weisong Mu
  • Computer Science
  • Neural Computing and Applications
  • 2021
TLDR
A convolution-based dual-stage attention (CDA) architecture combined with Long Short-Term Memory networks (LSTM) for univariate time series forecasting and carries a significant value not merely in adaptive modeling of deep learning in time series issues, but also in the field of univariate data processing and prediction. Expand
An evolutionary attention-based deep long short-term memory for time series prediction
Long-term prediction of time series is an important but challenging issue. Today, deep networks, especially Long short Term Memory (LSTM) networks, have been successfully used to predict time series.Expand
DTDR-ALSTM: Extracting dynamic time-delays to reconstruct multivariate data for improving attention-based LSTM industrial time series prediction models
TLDR
A novel approach to extracting dynamic time-delays to reconstruct (DTDR) multivariate data for an improved ALSTM prediction model that not only appropriately utilizes dynamics between the predicting and correlated variables, but also makes better attentions on key features extracted from optimum data. Expand
A dual‐stage attention‐based Conv‐LSTM network for spatio‐temporal correlation and multivariate time series prediction
TLDR
A convolution LSTM network model based on MTS prediction with two‐stage attention that is not only suitable for single‐step prediction of MTS, but also suitable for multistep prediction of time step in a certain range. Expand
Parallel spatio-temporal attention-based TCN for multivariate time series prediction
TLDR
This work argues that RNNs are fundamentally unsuited to long-horizon forecasting with complex data, and proposes a framework that combines a parallel spatio-temporal attention mechanism to extract dynamic internal correlations with stacked TCN backbones to extract features from different window sizes. Expand
Two-dimensional attention-based multi-input LSTM for time series prediction
TLDR
The proposed model is a method that introduces H-attention and T-att attention for output value and time step information to select useful information and outperforms existing models. Expand
Pay Attention to Evolution: Time Series Forecasting with Deep Graph-Evolution Learning
TLDR
An analysis of the intermediate weights arising from ReGENN is presented, showing that by looking at inter and intra-temporal relationships simultaneously, time-series forecasting is majorly improved if paying attention to how multiple multivariate data synchronously evolve. Expand
Multi-Attention Generative Adversarial Network for Multivariate Time Series Prediction
TLDR
The experiment results indicate that multi-attention mechanism is useful and the discrimination network can improve the performance in multivariate time series prediction, and an improved discrimination network is designed finally. Expand
VAECGAN: a generating framework for long-term prediction in multivariate time series
  • Xiang Yin, Yanni Han, Zhen Xu, Jie Liu
  • Cybersecurity
  • 2021
Long-term prediction is still a difficult problem in data mining. People usually use various kinds of methods of Recurrent Neural Network to predict. However, with the increase of the predictionExpand
Forecasting Corporate Financial Time Series using Multi-phase Attention Recurrent Neural Networks
TLDR
This paper proposes a new industry specific model that appropriately captures corporate financial time series, incorporating the industry trends and macroeconomic time series as side information and demonstrates the performance of the model through experiments with Japanese corporate financialTime series. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 58 REFERENCES
A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
TLDR
A dual-stage attention-based recurrent neural network (DA-RNN) to address the long-term temporal dependencies of the Nonlinear autoregressive exogenous model and can outperform state-of-the-art methods for time series prediction. Expand
Hierarchical Attention-Based Recurrent Highway Networks for Time Series Prediction
TLDR
An end-to-end deep learning model, i.e., Hierarchical attention-based Recurrent Highway Network (HRHN), which incorporates spatio-temporal feature extraction of exogenous variables and temporal dynamics modeling of target variables into a single framework is proposed. Expand
A Memory-Network Based Solution for Multivariate Time-Series Forecasting
TLDR
A deep learning based model named Memory Time-series network (MTNet) for time series forecasting, Inspired by Memory Network proposed for solving the question-answering task, which consists of a large memory component, three separate encoders, and an autoregressive component to train jointly. Expand
EA-LSTM: Evolutionary Attention-based LSTM for Time Series Prediction
TLDR
An evolutionary attention-based LSTM training with competitive random search is proposed for multivariate time series prediction, and the pattern for importance-based attention sampling can be confirmed during temporal relationship mining. Expand
Attention-based recurrent neural networks for accurate short-term and long-term dissolved oxygen prediction
TLDR
Experimental results show that attention-based RNN can achieve more accurate dissolved oxygen prediction in both short-term and long-term prediction. Expand
Position-Based Content Attention for Time Series Forecasting with Sequence-to-Sequence RNNs
TLDR
This extended attention model for sequence-to-sequence recurrent neural networks (RNNs) designed to capture (pseudo-)periods in time series is proposed and is shown to yield state-of-the-art performance for time series forecasting on several univariate and multivariate time series. Expand
Period-aware content attention RNNs for time series forecasting with missing values
TLDR
An extended attention model is proposed for sequence-to-sequence RNNs designed to capture periods in time series with or without missing values, and is shown to yield state-of-the-art performance for time series forecasting on several univariate and multivariate time series. Expand
An interpretable LSTM neural network for autoregressive exogenous model
TLDR
Variable importance in real datasets characterized by the variable attention is highly in line with that determined by statistical Granger causality test, which exhibits the prospect of multi-variable LSTM as a simple and uniform end-to-end framework for both forecasting and knowledge discovery. Expand
Multi-variable LSTM neural network for autoregressive exogenous model
TLDR
This paper proposes a multi-variable LSTM capable of accurate forecasting and variable importance interpretation for time series with exogenous variables and exhibits the prospect of multi- variable L STM as an end-to-end framework for both forecasting and knowledge discovery. Expand
GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction
TLDR
This paper predicts the readings of a geo-sensor over several future hours by using a multi-level attention-based recurrent neural network that considers multiple sensors’ readings, meteorological data, and spatial data. Expand
...
1
2
3
4
5
...