Multivariate Time Series Forecasting with Fourier Neural Filter

ICLR 2026 Conference Submission6038 Authors

Keywords: time series forecasting

Abstract: Multivariate time series forecasting has been suffering from the challenge of capturing both temporal dependencies within variables and spatial correlations across variables simultaneously. Current approaches predominantly repurpose backbones from Natural Language Processing (NLP) or Computer Vision (CV) (e.g., Transformers), which fail to adequately address the unique properties of time series (e.g., periodicity and fluctuation). The research community lacks dedicated backbones incorporating temporal-specific inductive biases, depending on domain-agnostic backbones supplemented with auxiliary techniques (e.g., signal decomposition). We introduce Fourier Neural Filter (FNF) as the backbone and Dual Branch Decoupler (DBD) as the architecture to provide exceptional learning capabilities and optimal learning pathways for spatiotemporal modeling, respectively. Our theoretical analysis proves that FNF integrates time-domain and frequency-domain analysis while enabling adaptive truncation of noise components within a unified backbone that extends naturally to spatial modeling. Through the lens of information bottleneck theory, we reveal that DBD delivers superior gradient flow and representation capacity, enabling it to effectively capture local and global, temporal and spatial information comprehensively. Our empirical evaluation on 12 public benchmark datasets, encompassing both multivariate long-term and short-term forecasting tasks, demonstrates state-of-the-art performance compared to existing advanced baseline models. Notably, our approach achieves these results without any auxiliary techniques, suggesting that properly designed neural architectures can capture the inherent properties of time series, potentially transforming time series modeling in scientific and industrial applications.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 6038