Saved in:
Bibliographic Details
Main Authors: Li, Chu, Xiao, Pingjia, Yuan, Qiping
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.06603
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911912354119680
author Li, Chu
Xiao, Pingjia
Yuan, Qiping
author_facet Li, Chu
Xiao, Pingjia
Yuan, Qiping
contents This study presents a novel time series prediction model, FPN-fusion, designed with linear computational complexity, demonstrating superior predictive performance compared to DLiner without increasing parameter count or computational demands. Our model introduces two key innovations: first, a Feature Pyramid Network (FPN) is employed to effectively capture time series data characteristics, bypassing the traditional decomposition into trend and seasonal components. Second, a multi-level fusion structure is developed to integrate deep and shallow features seamlessly. Empirically, FPN-fusion outperforms DLiner in 31 out of 32 test cases on eight open-source datasets, with an average reduction of 16.8% in mean squared error (MSE) and 11.8% in mean absolute error (MAE). Additionally, compared to the transformer-based PatchTST, FPN-fusion achieves 10 best MSE and 15 best MAE results, using only 8% of PatchTST's total computational load in the 32 test projects.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06603
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FPN-fusion: Enhanced Linear Complexity Time Series Forecasting Model
Li, Chu
Xiao, Pingjia
Yuan, Qiping
Machine Learning
Artificial Intelligence
This study presents a novel time series prediction model, FPN-fusion, designed with linear computational complexity, demonstrating superior predictive performance compared to DLiner without increasing parameter count or computational demands. Our model introduces two key innovations: first, a Feature Pyramid Network (FPN) is employed to effectively capture time series data characteristics, bypassing the traditional decomposition into trend and seasonal components. Second, a multi-level fusion structure is developed to integrate deep and shallow features seamlessly. Empirically, FPN-fusion outperforms DLiner in 31 out of 32 test cases on eight open-source datasets, with an average reduction of 16.8% in mean squared error (MSE) and 11.8% in mean absolute error (MAE). Additionally, compared to the transformer-based PatchTST, FPN-fusion achieves 10 best MSE and 15 best MAE results, using only 8% of PatchTST's total computational load in the 32 test projects.
title FPN-fusion: Enhanced Linear Complexity Time Series Forecasting Model
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.06603