{"ID":2834789,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.02070","arxiv_id":"2512.02070","title":"DPWMixer: Dual-Path Wavelet Mixer for Long-Term Time Series Forecasting","abstract":"Long-term time series forecasting (LTSF) is a critical task in computational intelligence. While Transformer-based models effectively capture long-range dependencies, they often suffer from quadratic complexity and overfitting due to data sparsity. Conversely, efficient linear models struggle to depict complex non-linear local dynamics. Furthermore, existing multi-scale frameworks typically rely on average pooling, which acts as a non-ideal low-pass filter, leading to spectral aliasing and the irreversible loss of high-frequency transients. In response, this paper proposes DPWMixer, a computationally efficient Dual-Path architecture. The framework is built upon a Lossless Haar Wavelet Pyramid that replaces traditional pooling, utilizing orthogonal decomposition to explicitly disentangle trends and local fluctuations without information loss. To process these components, we design a Dual-Path Trend Mixer that integrates a global linear mapping for macro-trend anchoring and a flexible patch-based MLP-Mixer for micro-dynamic evolution. Finally, An adaptive multi-scale fusion module then integrates predictions from diverse scales, weighted by channel stationarity to optimize synthesis. Extensive experiments on eight public benchmarks demonstrate that our method achieves a consistent improvement over state-of-the-art baselines. The code is available at https://github.com/hit636/DPWMixer.","short_abstract":"Long-term time series forecasting (LTSF) is a critical task in computational intelligence. While Transformer-based models effectively capture long-range dependencies, they often suffer from quadratic complexity and overfitting due to data sparsity. Conversely, efficient linear models struggle to depict complex non-line...","url_abs":"https://arxiv.org/abs/2512.02070","url_pdf":"https://arxiv.org/pdf/2512.02070v1","authors":"[\"Li Qianyang\",\"Zhang Xingjun\",\"Wang Shaoxun\",\"Wei Jia\"]","published":"2025-11-30T03:12:50Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":606444,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2834789,"paper_url":"https://arxiv.org/abs/2512.02070","paper_title":"DPWMixer: Dual-Path Wavelet Mixer for Long-Term Time Series Forecasting","repo_url":"https://github.com/hit636/DPWMixer","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}