Exploring Interpretable LSTM Neural Networks over Multi-Variable Data
This work addresses the need for interpretable forecasting in domains like finance or healthcare, though it is incremental as it builds on existing LSTM methods with added attention mechanisms.
The paper tackles the problem of providing interpretable insights alongside accurate predictions for multi-variable time series data using LSTM neural networks, resulting in enhanced prediction performance and evaluated interpretation results through experiments on real datasets.
For recurrent neural networks trained on time series with target and exogenous variables, in addition to accurate prediction, it is also desired to provide interpretable insights into the data. In this paper, we explore the structure of LSTM recurrent neural networks to learn variable-wise hidden states, with the aim to capture different dynamics in multi-variable time series and distinguish the contribution of variables to the prediction. With these variable-wise hidden states, a mixture attention mechanism is proposed to model the generative process of the target. Then we develop associated training methods to jointly learn network parameters, variable and temporal importance w.r.t the prediction of the target variable. Extensive experiments on real datasets demonstrate enhanced prediction performance by capturing the dynamics of different variables. Meanwhile, we evaluate the interpretation results both qualitatively and quantitatively. It exhibits the prospect as an end-to-end framework for both forecasting and knowledge extraction over multi-variable data.