Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting

TL;DR

This paper introduces Fourier Basis Mapping (FBM), a novel time-frequency learning framework for time series forecasting that enhances model performance by explicitly capturing frequency and temporal features.

Contribution

The paper proposes a new Fourier basis expansion method, FBM, addressing existing issues and integrating it with neural networks for improved time series forecasting.

Findings

FBM achieves state-of-the-art results on multiple datasets.

The method effectively captures frequency and temporal features.

FBM enhances various neural network architectures for forecasting.

Abstract

The integration of Fourier transform and deep learning opens new avenues for time series forecasting. We reconsider the Fourier transform from a basis functions perspective. Specifically, the real and imaginary parts of the frequency components can be regarded as the coefficients of cosine and sine basis functions at tiered frequency levels, respectively. We find that existing Fourier-based methods face inconsistent starting cycles and inconsistent series length issues. They fail to interpret frequency components precisely and overlook temporal information. Accordingly, the novel Fourier Basis Mapping (FBM) method addresses these issues by integrating time-frequency features through Fourier basis expansion and mapping in the time-frequency space. Our approach extracts explicit frequency features while preserving temporal characteristics. FBM supports plug-and-play integration with various types of neural networks by only adjusting the first initial projection layer for better performance. First, we propose FBM-L, FBM-NL, and FBM-NP to enhance linear, MLP-based, and Transformer-based models, respectively, demonstrating the effectiveness of time-frequency features. Next, we propose a synergetic model architecture, termed FBM-S, which decomposes the seasonal, trend, and interaction effects into three separate blocks, each designed to model time-frequency features in a specialized manner. Finally, we introduce several techniques tailored for time-frequency features, including interaction masking, centralization, patching, rolling window projection, and multi-scale down-sampling. The results are validated on diverse real-world datasets for both long-term and short-term forecasting tasks with SOTA performance.