WFTNet: Exploiting Global and Local Periodicity in Long-term Time Series Forecasting

Peiyuan Liu, Beiliang Wu, Naiqi Li, Tao Dai, Fengmao Lei, Jigang Bao, Yong Jiang, Shu-Tao Xia

TL;DR

WFTNet is a new architecture for long-term time series forecasting that combines the strengths of Fourier and Wavelet transforms. By using a novel Periodicity-Weighted Coefficient (PWC), the model adaptively balances global periodic patterns with local, fine-grained frequency variations, consistently outperforming current state-of-the-art models like TimesNet and FEDformer.

What Problem Does This Paper Address?

Predicting the long-term future of complex signals—like traffic flow, electricity consumption, or weather—is notoriously difficult. These signals often contain "periodicity," or patterns that repeat over time.

Current top-performing models (like TimesNet) use the Fourier Transform to identify these patterns. However, the Fourier Transform has a major limitation: it is a global operator. It excels at finding a steady heartbeat in a signal but struggles to capture "local" changes, such as a frequency shift that only happens for a short duration or non-stationary behaviors where patterns evolve. The authors argue that ignoring these local frequency structures leads to suboptimal forecasting.

Methods

The core innovation of WFTNet is the WFTBlock, which processes time series data through two parallel branches to capture a comprehensive "temporal-frequency" view.

  1. The Fourier Branch: This branch uses the Fast Fourier Transform (FFT) to identify the most dominant global frequencies. Following the approach of TimesNet, it reshapes 1D time series into 2D tensors based on these periods, allowing the model to use 2D convolutions to analyze intra-period and inter-period variations.
  2. The Wavelet Branch: Recognizing that Fourier misses local context, this branch employs the Continuous Wavelet Transform (CWT). Wavelets are mathematically designed to provide high resolution in both time and frequency domains, making them perfect for spotting transient or localized periodic structures.
  3. Periodicity-Weighted Coefficient (PWC): This is the "brain" of the fusion stage. The PWC ($\alpha$) is a calculated metric that measures the relative strength of global periodicity in a signal.
  4. If a signal is highly periodic (like electricity usage), $\alpha$ is high, and the model relies more on the Fourier branch.
  5. If the signal is irregular or non-stationary, $\alpha$ is low, and the model leans on the Wavelet branch.
Fig. 1: Overall architecture of WFTNet (left) and details of WFTBlock (right). The encoder and decoder manage input normalization, embedding, and output projection. WFTBlocks transform the 1D time series into 2D repre- sentations using FFT for global periodic patterns and CWT for local features.

Datasets

The authors evaluated WFTNet on seven standard benchmark datasets for long-term forecasting:

  • ETT (Electricity Transformer Temperature): Four sub-datasets (ETTh1, ETTh2, ETTm1, ETTm2) recorded at different granularities.
  • Traffic: Hourly road occupancy rates.
  • ECL (Electricity Consumption Load): Hourly electricity consumption of 321 clients.
  • Weather: Local climatological data containing 21 variables.

Key Insights and Ideas

  • Global vs. Local Synergy: The paper demonstrates that global and local periodicities are not mutually exclusive; they are complementary. A model that only looks at one (like TimesNet with Fourier) is essentially "blind" to half the story.
  • Adaptive Fusion is Key: Different datasets have vastly different periodic characteristics. As shown in Figure 2, the ECL dataset has very clear, strong periodicity, while the ETTh2 dataset is much noisier. The PWC allows WFTNet to change its strategy dynamically for each dataset—or even each channel within a dataset—without manual tuning.
Fig. 2: Visualization of the normalized mean channel values for the ECL and ETTh2 datasets. The plot re- veals stronger periodicity in ECL compared to ETTh2.

Key Results

WFTNet achieved impressive results across the board, securing the best performance in 19 out of 32 tested scenarios (combinations of datasets and prediction horizons).

  • Superiority over SOTA: WFTNet consistently beat TimesNet, which was the previous benchmark for frequency-based forecasting. For example, on the ECL dataset at a prediction length of 96, WFTNet achieved an MSE of 0.164, compared to TimesNet's 0.167.
  • Ablation Success: The authors proved the necessity of both branches. In their ablation study (Table 2), the full WFTNet outperformed both "Fourier-Only" and "Wavelet-Only" versions, validating that the PWC-based fusion effectively harvests the best of both worlds.
Table 1: Quantitative evaluation of long-term time series forecasting models with varying output sequence lengths T ∈{96, 192, 336, 720}. Input sequence is fixed at 96. Best performances are highlighted in red and second-best are underlined in blue.

Limitations and Future Work

While the paper presents a strong case for WFTNet, a few areas remain for exploration:

  • Computational Overhead: The Continuous Wavelet Transform (CWT) can be computationally more expensive than the FFT. While the authors use efficient convolutional structures, the scaling of this approach to extremely high-dimensional or high-frequency data could be a bottleneck.
  • Mother Wavelet Selection: The study primarily uses the Morlet wavelet. Exploring how different "mother wavelets" affect performance on specific types of time series (e.g., financial vs. physical sensors) could be a fruitful research direction.
  • Hyperparameter Sensitivity: The fusion equation uses a hyperparameter $n$ to modulate the PWC. The paper does not discuss in depth how sensitive the model is to this specific value across different domains.

Summary updated

Abstract

Recent CNN and Transformer-based models tried to utilize frequency and periodicity information for long-term time series forecasting. However, most existing work is based on Fourier transform, which cannot capture fine-grained and local frequency structure. In this paper, we propose a Wavelet-Fourier Transform Network (WFTNet) for long-term time series forecasting. WFTNet utilizes both Fourier and wavelet transforms to extract comprehensive temporal-frequency information from the signal, where Fourier transform captures the global periodic patterns and wavelet transform captures the local ones. Furthermore, we introduce a Periodicity-Weighted Coefficient (PWC) to adaptively balance the importance of global and local frequency patterns. Extensive experiments on various time series datasets show that WFTNet consistently outperforms other state-of-the-art baseline. Code is available at https://github.com/Hank0626/WFTNet.
BibTeX
@inproceedings{liu2024wftnet,
  author = {Peiyuan Liu and Beiliang Wu and Naiqi Li and Tao Dai and Fengmao Lei and Jigang Bao and Yong Jiang and Shu-Tao Xia},
  title = {{WFTNet: Exploiting Global and Local Periodicity in Long-term Time Series Forecasting}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2024},
  doi = {10.1109/icassp48485.2024.10446883},
}
Figure