What type of study is this?

This is a Quantitative Study study.

September 12, 2025

VLinear: Enhanced linear complexity time series forecasting model

Key Points

VLinear achieves a 16.8% reduction in mean squared error compared to DLiner, showing effective predictive performance.
Out of 32 test cases, VLinear surpasses DLiner in 31, indicating its reliability across diverse datasets.
Employing a Feature Pyramid Network, VLinear captures time series characteristics without traditional decomposition.
Using only 8% of PatchTST's computational load, VLinear demonstrates high efficiency in model performance.

Abstract

This study presents a novel time series prediction model(VLinear), 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-layer fusion structure is developed to integrate deep and shallow features seamlessly. Empirically, VLinear 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, VLinear achieves 10 best MSE and 15 best MAE results, using only 8% of PatchTST’s total computational load in the 32 test projects.

Mark Helpful

Bookmark

Relay