Multi-Scale Dilated Convolution Network for Long-Term Time Series Forecasting
This work addresses long-term time series forecasting for decision-making and planning, presenting an incremental improvement with a novel hybrid method.
The paper tackled the challenge of capturing long-term dependencies in time series forecasting by proposing the Multi-Scale Dilated Convolution Network (MSDCN), which outperformed prior state-of-the-art methods on eight benchmark datasets and achieved significant inference speed improvements.
Accurate forecasting of long-term time series has important applications for decision making and planning. However, it remains challenging to capture the long-term dependencies in time series data. To better extract long-term dependencies, We propose Multi Scale Dilated Convolution Network (MSDCN), a method that utilizes a shallow dilated convolution architecture to capture the period and trend characteristics of long time series. We design different convolution blocks with exponentially growing dilations and varying kernel sizes to sample time series data at different scales. Furthermore, we utilize traditional autoregressive model to capture the linear relationships within the data. To validate the effectiveness of the proposed approach, we conduct experiments on eight challenging long-term time series forecasting benchmark datasets. The experimental results show that our approach outperforms the prior state-of-the-art approaches and shows significant inference speed improvements compared to several strong baseline methods.