Work

KEDformer: Knowledge extraction seasonal trend decomposition for long-term sequence prediction

Year: 2025

Type: article

Abstract: Time series forecasting is essential in energy, finance, and meteorology. However, existing Transformer-based models face challenges with computational inefficiency and poor generalization for long-term sequences. To address these issues, this study proposes the KEDformer framework. It integrates knowledge extraction and seasonal-trend decomposition to optimize model performance. By leveraging sparse attention and autocorrelation, KEDformer reduces computational complexity from O(L2) to O(L log L), enhancing the model's ability to capture both short-term fluctuations and long-term patterns. Experiments on five public datasets covering energy, transportation, and weather tasks demonstrate that KEDformer consistently outperforms traditional models, with an average improvement of 10.4% in MSE prediction accuracy and 2.9% in MAE prediction accuracy.

Source: PLoS ONE

DOI: 10.1371/journal.pone.0335047

Authors: Zhenkai Qin, Baozhong Wei, Caifeng Gao, Jianyuan Ni

Institutions: Guangxi Police College, Juniata College

Language: English

Topic: Time Series Analysis and Forecasting

Subfield: Signal Processing

Field: Computer Science

Domain: Physical Sciences

SDGs: Climate action, Affordable and clean energy

Open Access status: gold

Estimated APC paid: $2,382