Learning the Dynamic Correlations and Mitigating Noise by Hierarchical Convolution for Long-term Sequence Forecasting
This work improves forecasting accuracy for time series applications, though it appears incremental as it builds on existing deep learning approaches with specific architectural enhancements.
The paper tackles long-term sequence forecasting by addressing dynamic variable interactions and evolutionary noise, proposing HMNet which achieves 10.6% MSE and 5.7% MAE improvements over state-of-the-art models on five benchmarks.
Deep learning algorithms, especially Transformer-based models, have achieved significant performance by capturing long-range dependencies and historical information. However, the power of convolution has not been fully investigated. Moreover, most existing works ignore the dynamic interaction among variables and evolutionary noise in series. Addressing these issues, we propose a Hierarchical Memorizing Network (HMNet). In particular, a hierarchical convolution structure is introduced to extract the information from the series at various scales. Besides, we propose a dynamic variable interaction module to learn the varying correlation and an adaptive denoising module to search and exploit similar patterns to alleviate noises. These modules can cooperate with the hierarchical structure from the perspective of fine to coarse grain. Experiments on five benchmarks demonstrate that HMNet significantly outperforms the state-of-the-art models by 10.6% on MSE and 5.7% on MAE. Our code is released at https://github.com/yzhHoward/HMNet.