Multi-Scale Dilated Convolution Network for Long-Term Time Series Forecasting

TL;DR

This paper introduces a Multi-Scale Dilated Convolution Network (MSDCN) that effectively captures long-term dependencies in time series data for improved long-term forecasting accuracy and speed.

Contribution

The paper presents a novel shallow dilated convolution architecture with multi-scale sampling and integrates an autoregressive model for enhanced long-term forecasting.

Findings

Outperforms state-of-the-art methods on eight benchmark datasets

Achieves significant inference speed improvements

Effectively captures long-term dependencies in time series

Abstract

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.