Abstract:Accurate traffic forecasting is essential for intelligent transportation systems, supporting a wide range of real-world applications. However, it remains challenging due to two key factors:~(1) Traffic series contain heterogeneous temporal patterns, where stable periodic regularities coexist with event-driven fluctuations. Existing methods often treat them within a unified representation, limiting their ability to capture fine-grained temporal dynamics.~(2)Spatial dependencies among nodes are inherently dynamic and sparse, while dense all-pairs attention often introduces redundant interactions and amplifies noise. To address these issues, we propose ADMFormer, an Adaptive-Decomposition Transformer with Time-Varying Masked Spatial Attention. Specifically, ADMFormer first employs a time-node adaptive gating mechanism to decouple traffic signals into dominant regularities and residual fluctuations that vary across time and nodes. A dual-branch temporal module is then designed to separately capture global periodic dependencies and high-frequency irregular variations from these two decomposed components. Furthermore, ADMFormer introduces a time-varying masked spatial attention that sparsifies spatial interactions based on real-time traffic states, thereby effectively preserving dynamic and informative dependencies. Extensive experiments on four real-world datasets demonstrate that ADMFormer achieves state-of-the-art performance.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.25543 [cs.AI] |
| (or arXiv:2605.25543v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.25543 arXiv-issued DOI via DataCite (pending registration) |
From: Ruiwen Gu [view email]
[v1]
Mon, 25 May 2026 08:00:02 UTC (1,594 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。