Filter then Attend: Improving attention-based Time Series Forecasting with Spectral Filtering
Dayag, Elisha, Van Tran, Nhat Thanh, Xin, Jack
–arXiv.org Artificial Intelligence
Transformer-based models are at the forefront in long time-series forecasting (LTSF). While in many cases, these models are able to achieve state of the art results, they suffer from a bias toward low-frequencies in the data and high computational and memory requirements. Recent work has established that learnable frequency filters can be an integral part of a deep forecasting model by enhancing the model's spectral utilization. These works choose to use a multilayer perceptron to process their filtered signals and thus do not solve the issues found with transformer-based models. In this paper, we establish that adding a filter to the beginning of transformer-based models enhances their performance in long time-series forecasting. We add learnable filters, which only add an additional $\approx 1000$ parameters to several transformer-based models and observe in multiple instances 5-10 \% relative improvement in forecasting performance. Additionally, we find that with filters added, we are able to decrease the embedding dimension of our models, resulting in transformer-based architectures that are both smaller and more effective than their non-filtering base models. We also conduct synthetic experiments to analyze how the filters enable Transformer-based models to better utilize the full spectrum for forecasting.
arXiv.org Artificial Intelligence
Aug-29-2025
- Country:
- North America > United States > California > Orange County > Irvine (0.14)
- Genre:
- Research Report (0.82)
- Industry:
- Energy (0.95)
- Technology: