ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series Forecasting
This work addresses the challenge of multi-step-ahead forecasting for time-series data, which is incremental as it modifies existing deep learning approaches to improve performance.
The authors tackled the problem of multi-step-ahead time-series forecasting by proposing ForecastNet, a time-variant deep feed-forward neural network architecture, and demonstrated that it outperforms statistical and deep learning benchmark models on several datasets.
Recurrent and convolutional neural networks are the most common architectures used for time series forecasting in deep learning literature. These networks use parameter sharing by repeating a set of fixed architectures with fixed parameters over time or space. The result is that the overall architecture is time-invariant (shift-invariant in the spatial domain) or stationary. We argue that time-invariance can reduce the capacity to perform multi-step-ahead forecasting, where modelling the dynamics at a range of scales and resolutions is required. We propose ForecastNet which uses a deep feed-forward architecture to provide a time-variant model. An additional novelty of ForecastNet is interleaved outputs, which we show assist in mitigating vanishing gradients. ForecastNet is demonstrated to outperform statistical and deep learning benchmark models on several datasets.