MS-DFTVNet:A Long-Term Time Series Prediction Method Based on Multi-Scale Deformable Convolution
This work addresses the problem of accurate long-term forecasting for time series data, offering a novel convolutional approach that outperforms existing methods, though it is incremental in advancing model architectures.
The paper tackles long-term time series prediction by proposing MS-DFTVNet, a multi-scale 3D deformable convolutional framework that captures cross-period interactions and variable dependencies, achieving an average improvement of about 7.5% across six public datasets and setting new state-of-the-art results.
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.