AWEMixer: Adaptive Wavelet-Enhanced Mixer Network for Long-Term Time Series Forecasting

TL;DR

AWEMixer is a novel neural network that adaptively combines wavelet and Fourier transforms to improve long-term time series forecasting accuracy in IoT environments, especially for non-stationary and multi-scale signals.

Contribution

The paper introduces AWEMixer, which integrates a Frequency Router and a Coherent Gated Fusion Block for enhanced time-frequency localization and noise robustness in long-term forecasting.

Findings

Outperforms recent state-of-the-art models on seven benchmarks.

Achieves consistent improvements over transformer and MLP-based models.

Demonstrates robustness to noise and non-stationary signals.

Abstract

Forecasting long-term time series in IoT environments remains a significant challenge due to the non-stationary and multi-scale characteristics of sensor signals. Furthermore, error accumulation causes a decrease in forecast quality when predicting further into the future. Traditional methods are restricted to operate in time-domain, while the global frequency information achieved by Fourier transform would be regarded as stationary signals leading to blur the temporal patterns of transient events. We propose AWEMixer, an Adaptive Wavelet-Enhanced Mixer Network including two innovative components: 1) a Frequency Router designs to utilize the global periodicity pattern achieved by Fast Fourier Transform to adaptively weight localized wavelet subband, and 2) a Coherent Gated Fusion Block to achieve selective integration of prominent frequency features with multi-scale temporal representation through cross-attention and gating mechanism, which realizes accurate time-frequency localization while remaining robust to noise. Seven public benchmarks validate that our model is more effective than recent state-of-the-art models. Specifically, our model consistently achieves performance improvement compared with transformer-based and MLP-based state-of-the-art models in long-sequence time series forecasting. Code is available at https://github.com/hit636/AWEMixer