Affirm: Interactive Mamba with Adaptive Fourier Filters for Long-term Time Series Forecasting
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (20) , 21599-21607
Abstract
In long-term series forecasting (LTSF), it is imperative for models to adeptly discern and distill from historical time series data to forecast future states. Although Transformer-based models excel at capturing long-term dependencies in LTSF, their practical use is limited by issues like computational inefficiency, noise sensitivity, and overfitting on smaller datasets. Therefore, we introduce a novel time series lightweight interactive Mamba with an adaptive Fourier filter model (Affirm). Specifically, (i) we propose an adaptive Fourier filter block. This neural operator employs Fourier analysis to refine feature representation, reduces noise with learnable adaptive thresholds, and captures inter-frequency interactions using global and local semantic adaptive Fourier filters via element-wise multiplication. (ii) A dual interactive Mamba block is introduced to facilitate efficient intra-modal interactions at different granularities, capturing more detailed local features and broad global contextual information, providing a more comprehensive representation for LTSF. Extensive experiments on multiple benchmarks demonstrate that Affirm consistently outperforms existing SOTA methods, offering a superior balance of accuracy and efficiency, making it ideal for various challenging scenarios with noise levels and data sizes.Keywords
This publication has 7 references indexed in Scilit:
- DTMamba : Dual Twin Mamba for Time Series ForecastingTsinghua Science and Technology, 2026
- PyramidMamba: Rethinking pyramid feature fusion with selective space state model for semantic segmentation of remote sensing imageryInternational Journal of Applied Earth Observation and Geoinformation, 2025
- Effective LSTMs with seasonal-trend decomposition and adaptive learning and niching-based backtracking search algorithm for time series forecastingExpert Systems with Applications, 2023
- Frequency-domain MLPs are More Effective Learners in Time Series Forecasting2023
- Research on noise reduction method for ship radiate noise based on secondary decompositionOcean Engineering, 2022
- FiLM: Frequency Improved Legendre Memory Model for Long-Term Time Series Forecasting2022
- Theory and Application of Digital Signal ProcessingIEEE Transactions on Systems, Man, and Cybernetics, 1978