AWGformer: Adaptive Wavelet-Guided Transformer for Multi-Resolution Time Series Forecasting
This work addresses the challenge of capturing patterns across multiple temporal scales for multi-variate time series forecasting, with potential applications in domains like finance or IoT, but it appears incremental as it builds on existing transformer and wavelet techniques.
The paper tackled the problem of multi-resolution time series forecasting by introducing AWGformer, which integrates adaptive wavelet decomposition with cross-scale attention mechanisms, achieving significant average improvements over state-of-the-art methods on benchmark datasets.
Time series forecasting requires capturing patterns across multiple temporal scales while maintaining computational efficiency. This paper introduces AWGformer, a novel architecture that integrates adaptive wavelet decomposition with cross-scale attention mechanisms for enhanced multi-variate time series prediction. Our approach comprises: (1) an Adaptive Wavelet Decomposition Module (AWDM) that dynamically selects optimal wavelet bases and decomposition levels based on signal characteristics; (2) a Cross-Scale Feature Fusion (CSFF) mechanism that captures interactions between different frequency bands through learnable coupling matrices; (3) a Frequency-Aware Multi-Head Attention (FAMA) module that weights attention heads according to their frequency selectivity; (4) a Hierarchical Prediction Network (HPN) that generates forecasts at multiple resolutions before reconstruction. Extensive experiments on benchmark datasets demonstrate that AWGformer achieves significant average improvements over state-of-the-art methods, with particular effectiveness on multi-scale and non-stationary time series. Theoretical analysis provides convergence guarantees and establishes the connection between our wavelet-guided attention and classical signal processing principles.