Dualformer: Time-Frequency Dual Domain Learning for Long-term Time Series Forecasting

TL;DR

Dualformer introduces a dual-domain approach with hierarchical frequency sampling and adaptive weighting to improve long-term time series forecasting by better preserving high-frequency details and modeling frequency components.

Contribution

It proposes a novel dual-branch transformer framework with frequency-aware modules that enhance frequency modeling and information preservation in long-term forecasting.

Findings

Outperforms existing models on eight benchmarks.

Effectively preserves high-frequency information.

Shows robustness on heterogeneous and weakly periodic data.

Abstract

Transformer-based models, despite their promise for long-term time series forecasting (LTSF), suffer from an inherent low-pass filtering effect that limits their effectiveness. This issue arises due to undifferentiated propagation of frequency components across layers, causing a progressive attenuation of high-frequency information crucial for capturing fine-grained temporal variations. To address this limitation, we propose Dualformer, a principled dual-domain framework that rethinks frequency modeling from a layer-wise perspective. Dualformer introduces three key components: (1) a dual-branch architecture that concurrently models complementary temporal patterns in both time and frequency domains; (2) a hierarchical frequency sampling module that allocates distinct frequency bands to different layers, preserving high-frequency details in lower layers while modeling low-frequency trends in deeper layers; and (3) a periodicity-aware weighting mechanism that dynamically balances contributions from the dual branches based on the harmonic energy ratio of inputs, supported theoretically by a derived lower bound. This design enables structured frequency modeling and adaptive integration of time-frequency features, effectively preserving high-frequency information and enhancing generalization. Extensive experiments conducted on eight widely used benchmarks demonstrate Dualformer's robustness and superior performance, particularly on heterogeneous or weakly periodic data. Our code is publicly available at https://github.com/Akira-221/Dualformer.