{"ID":2871328,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18135","arxiv_id":"2509.18135","title":"SDGF: Fusing Static and Multi-Scale Dynamic Correlations for Multivariate Time Series Forecasting","abstract":"Accurate multivariate time series forecasting hinges on inter-series correlations, which often evolve in complex ways across different temporal scales. Existing methods are limited in modeling these multi-scale dependencies and struggle to capture their intricate and evolving nature. To address this challenge, this paper proposes a novel Static-Dynamic Graph Fusion network (SDGF), whose core lies in capturing multi-scale inter-series correlations through a dual-path graph structure learning approach. Specifically, the model utilizes a static graph based on prior knowledge to anchor long-term, stable dependencies, while concurrently employing Multi-level Wavelet Decomposition to extract multi-scale features for constructing an adaptively learned dynamic graph to capture associations at different scales. We design an attention-gated module to fuse these two complementary sources of information intelligently, and a multi-kernel dilated convolutional network is then used to deepen the understanding of temporal patterns. Comprehensive experiments on multiple widely used real-world benchmark datasets demonstrate the effectiveness of our proposed model. Code is available at https://github.com/shaoxun6033/SDGFNet.","short_abstract":"Accurate multivariate time series forecasting hinges on inter-series correlations, which often evolve in complex ways across different temporal scales. Existing methods are limited in modeling these multi-scale dependencies and struggle to capture their intricate and evolving nature. To address this challenge, this pap...","url_abs":"https://arxiv.org/abs/2509.18135","url_pdf":"https://arxiv.org/pdf/2509.18135v2","authors":"[\"Shaoxun Wang\",\"Xingjun Zhang\",\"Qianyang Li\",\"Jiawei Cao\",\"Zhendong Tan\"]","published":"2025-09-14T11:23:12Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":609848,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2871328,"paper_url":"https://arxiv.org/abs/2509.18135","paper_title":"SDGF: Fusing Static and Multi-Scale Dynamic Correlations for Multivariate Time Series Forecasting","repo_url":"https://github.com/shaoxun6033/SDGFNet","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}