Long-term time series forecasting (LTSF) is a challenging task that has been investigated in various domains such as finance investment, health care, traffic, and weather forecasting. In recent years, Linear-based LTSF models showed better performance, pointing out the problem of Transformer-based approaches causing temporal information loss. However, Linear-based approach has also limitations that the model is too simple to comprehensively exploit the characteristics of the dataset. To solve these limitations, we propose LTSF-DNODE, which applies a model based on linear ordinary differential equations (ODEs) and a time series decomposition method according to data statistical characteristics. We show that LTSF-DNODE outperforms the baselines on various real-world datasets. In addition, for each dataset, we explore the impacts of regularization in the neural ordinary differential equation (NODE) framework.
@article{arxiv.2311.04522,
title = {Long-term Time Series Forecasting based on Decomposition and Neural Ordinary Differential Equations},
author = {Seonkyu Lim and Jaehyeon Park and Seojin Kim and Hyowon Wi and Haksoo Lim and Jinsung Jeon and Jeongwhan Choi and Noseong Park},
journal= {arXiv preprint arXiv:2311.04522},
year = {2023}
}