Problem
Research questions and friction points this paper is trying to address.
long-term time series forecasting
multi-scale information
temporal downsampling
information loss
hierarchical temporal patterns
Recovering Lost Details: Multi-Scale Frequency Compensation for Long-Term Time Series Forecasting
🤖 AI Summary
本文提出了一种多尺度小波混合模型MWMixer，通过双向频带混合策略恢复时间序列中的丢失细节，并采用动态自适应融合模块和跨尺度一致性损失来提高长期预测准确性。
📝 Abstract
Long-term time series forecasting has made significant progress by leveraging multi-scale information to capture hierarchical temporal patterns and model long-range dependencies. However, temporal downsampling in existing multi-scale methods inevitably smooths detailed temporal fluctuations, and this information loss is further aggravated by their emphasis on dominant trends across scales, resulting in insufficiently expressive representations. To address this, we propose a Multi-Scale Wavelet Mixing (MWMixer) model, which incorporates a Bidirectional Frequency-Bands Mixing strategy to recover lost temporal details across scales, enabling complementary cross-scale information interactions. Then, a Dynamic Scale-Adaptive Fusion module learns time-varying weights for each scale to fuse multi-scale forecasts into the final prediction, enhancing the flexibility of multi-scale aggregation. In addition, a cross-scale consistency loss aligns each coarse-scale prediction with the interval-averaged fine-scale outputs, while a multi-scale supervision loss enforces prediction accuracy at each scale, promoting consistent learning across scales. Extensive experiments on seven real-world datasets demonstrate that MWMixer achieves competitive performance in long-term forecasting.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-Scale Wavelet Mixing (MWMixer)
Bidirectional Frequency-Bands Mixing
Dynamic Scale-Adaptive Fusion
Cross-scale Consistency Loss
Multi-scale Supervision Loss
🔎 Similar Papers
No similar papers found.
