解耦异构交通动态用于多步交通预测：基于自适应谱分解
Disentangling Heterogeneous Traffic Dynamics for Multi-Step Traffic Forecasting via Adaptive Spectral Decomposition
查看机构详情
- Beijing Normal-Hong Kong Baptist University（北京师范大学-香港浸会大学联合国际学院）
- Dalian Maritime University（大连海事大学）
- National Chung Hsing University（国立中兴大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对多步交通预测中异构动态难以分离的问题，提出自适应分解网络ADNet，通过可学习谱分解将信号分为主导与残差组件，并双分支建模，在TraffiDent数据集上多数比较中取得最优。
中文摘要 AI 辅助
准确的多步交通预测仍然具有挑战性，因为观测到的交通信号包含具有不同特征和可预测性水平的异构时间动态。现有方法通常将这些动态建模在统一表示中，或依赖于预定义的分解规则，这可能限制其灵活分离持续性模式与快速变化波动的能力。为解决此问题，我们提出了自适应分解网络（ADNet），一种组件特定的预测框架，能够自适应地将交通动态解耦为主导组件和残差组件。ADNet引入了一种可学习的互补谱分解机制，该机制确定每个频率区间对两个组件的贡献。与硬频率划分不同，每个频率区间可以以不同的学习比例对两个组件均有贡献，从而允许分解与预测目标联合优化。重建的组件随后由两个专用的时空预测分支建模，其预测被整合以生成最终的多步预测。在TraffiDent数据集的Alameda和Orange区域上的实验表明，ADNet在24个报告的区域-预测时域-指标比较中取得了20个最佳性能，在较长预测时域上尤为明显。容量控制的消融实验进一步表明，可学习的分解显著优于固定分解，并在双分支架构之外提供了额外改进。这些结果证明了自适应分解和组件特定建模在多步交通预测中的有效性。
英文摘要
Accurate multi-step traffic forecasting remains challenging because observed traffic signals contain heterogeneous temporal dynamics with different characteristics and levels of predictability. Existing approaches typically model these dynamics within a unified representation or rely on predefined decomposition rules, which may limit their ability to flexibly separate persistent patterns from rapidly varying fluctuations. To address this issue, we propose the Adaptive Decomposition Network (ADNet), a component-specific forecasting framework that adaptively disentangles traffic dynamics into dominant and residual components. ADNet introduces a learnable complementary spectral decomposition mechanism that determines the contribution of each frequency bin to the two components. Unlike hard frequency partitioning, every frequency bin can contribute to both components with different learned proportions, allowing the decomposition to be optimized jointly with the forecasting objective. The reconstructed components are then modeled by two dedicated spatiotemporal forecasting branches, and their predictions are integrated to generate the final multi-step forecast. Experiments on the Alameda and Orange regions of the TraffiDent dataset show that ADNet achieves the best performance in 20 of the 24 reported region-horizon-metric comparisons, with particularly clear gains at longer forecasting horizons. Capacity-controlled ablation experiments further show that the learnable decomposition substantially outperforms a fixed decomposition and provides additional improvements beyond the dual-branch architecture alone. These results demonstrate the effectiveness of adaptive decomposition and component-specific modeling for multi-step traffic forecasting.
