EA-LSTM: Evolutionary Attention-based LSTM for Time Series Prediction
This work addresses a domain-specific issue in time series prediction, offering an incremental improvement for researchers and practitioners in fields like finance or forecasting.
The paper tackled the problem of insufficient attention allocation in LSTM models for multivariate time series prediction by proposing an evolutionary attention-based LSTM with competitive random search, achieving competitive prediction performance compared to baseline methods.
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.