Saved in:
Bibliographic Details
Main Authors: Li, Chenghan, Li, Mingchen, Liao, Yipu, Diao, Ruisheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.17253
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908572594470912
author Li, Chenghan
Li, Mingchen
Liao, Yipu
Diao, Ruisheng
author_facet Li, Chenghan
Li, Mingchen
Liao, Yipu
Diao, Ruisheng
contents Research on long-term time series prediction has primarily relied on Transformer and MLP models, while the potential of convolutional networks in this domain remains underexplored. To address this, we propose a novel multi-scale time series reshape module that effectively captures cross-period patch interactions and variable dependencies. Building on this, we develop MS-DFTVNet, the multi-scale 3D deformable convolutional framework tailored for long-term forecasting. Moreover, to handle the inherently uneven distribution of temporal features, we introduce a context-aware dynamic deformable convolution mechanism, which further enhances the model's ability to capture complex temporal patterns. Extensive experiments demonstrate that MS-DFTVNet not only significantly outperforms strong baselines but also achieves an average improvement of about 7.5% across six public datasets, setting new state-of-the-art results.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17253
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MS-DFTVNet:A Long-Term Time Series Prediction Method Based on Multi-Scale Deformable Convolution
Li, Chenghan
Li, Mingchen
Liao, Yipu
Diao, Ruisheng
Machine Learning
Artificial Intelligence
Research on long-term time series prediction has primarily relied on Transformer and MLP models, while the potential of convolutional networks in this domain remains underexplored. To address this, we propose a novel multi-scale time series reshape module that effectively captures cross-period patch interactions and variable dependencies. Building on this, we develop MS-DFTVNet, the multi-scale 3D deformable convolutional framework tailored for long-term forecasting. Moreover, to handle the inherently uneven distribution of temporal features, we introduce a context-aware dynamic deformable convolution mechanism, which further enhances the model's ability to capture complex temporal patterns. Extensive experiments demonstrate that MS-DFTVNet not only significantly outperforms strong baselines but also achieves an average improvement of about 7.5% across six public datasets, setting new state-of-the-art results.
title MS-DFTVNet:A Long-Term Time Series Prediction Method Based on Multi-Scale Deformable Convolution
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.17253