{"ID":2869292,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.14868","arxiv_id":"2509.14868","title":"DPANet: Dual Pyramid Attention Network for Multivariate Time Series Forecasting","abstract":"Long-term time series forecasting (LTSF) is hampered by the challenge of modeling complex dependencies that span multiple temporal scales and frequency resolutions. Existing methods, including Transformer and MLP-based models, often struggle to capture these intertwined characteristics in a unified and structured manner. We propose the Dual Pyramid Attention Network (DPANet), a novel architecture that explicitly decouples and concurrently models temporal multi-scale dynamics and spectral multi-resolution periodicities. DPANet constructs two parallel pyramids: a Temporal Pyramid built on progressive downsampling, and a Frequency Pyramid built on band-pass filtering. The core of our model is the Cross-Pyramid Fusion Block, which facilitates deep, interactive information exchange between corresponding pyramid levels via cross-attention. This fusion proceeds in a coarse-to-fine hierarchy, enabling global context to guide local representation learning. Extensive experiments on public benchmarks show that DPANet achieves state-of-the-art performance, significantly outperforming prior models. Code is available at https://github.com/hit636/DPANet.","short_abstract":"Long-term time series forecasting (LTSF) is hampered by the challenge of modeling complex dependencies that span multiple temporal scales and frequency resolutions. Existing methods, including Transformer and MLP-based models, often struggle to capture these intertwined characteristics in a unified and structured manne...","url_abs":"https://arxiv.org/abs/2509.14868","url_pdf":"https://arxiv.org/pdf/2509.14868v2","authors":"[\"Qianyang Li\",\"Xingjun Zhang\",\"Shaoxun Wang\",\"Jia Wei\"]","published":"2025-09-18T11:35:21Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":609668,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2869292,"paper_url":"https://arxiv.org/abs/2509.14868","paper_title":"DPANet: Dual Pyramid Attention Network for Multivariate Time Series Forecasting","repo_url":"https://github.com/hit636/DPANet","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}