EA-LSTM: Evolutionary Attention-based LSTM for Time Series Prediction

TL;DR

This paper introduces EA-LSTM, an innovative time series prediction model that combines evolutionary attention learning with LSTMs, enhancing the model's ability to focus on important features over multiple time steps.

Contribution

It proposes a novel evolutionary attention-based training approach for LSTMs, utilizing competitive random search to optimize attention parameters for improved multivariate time series prediction.

Findings

Achieves competitive prediction accuracy compared to baseline methods

Demonstrates effective attention sampling through evolutionary learning

Enhances LSTM's ability to capture long-term dependencies

Abstract

Time series prediction with deep learning methods, especially long short-term memory neural networks (LSTMs), have scored significant achievements in recent years. Despite the fact that the LSTMs can help to capture long-term dependencies, its ability to pay different degree of attention on sub-window feature within multiple time-steps is insufficient. To address this issue, an evolutionary attention-based LSTM training with competitive random search is proposed for multivariate time series prediction. By transferring shared parameters, an evolutionary attention learning approach is introduced to the LSTMs model. Thus, like that for biological evolution, the pattern for importance-based attention sampling can be confirmed during temporal relationship mining. To refrain from being trapped into partial optimization like traditional gradient-based methods, an evolutionary computation inspired competitive random search method is proposed, which can well configure the parameters in the attention layer. Experimental results have illustrated that the proposed model can achieve competetive prediction performance compared with other baseline methods.