如何不同于过去？基于自监督偏差学习的时空时间序列预测
How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning
AI总结：
本文提出ST-SSDL框架，通过自监督偏差学习捕获时空预测中当前输入与历史模式的动态偏差，利用原型离散化和双重辅助损失优化，在六个基准数据集上超越现有方法。
摘要：
时空预测对于交通管理和城市计算等实际应用至关重要。尽管近期方法已显示出更高的准确性，但它们往往未能考虑当前输入与历史模式之间的动态偏差。这些偏差包含可能显著影响模型性能的关键信号。为填补这一空白，我们提出ST-SSDL，一个时空时间序列预测框架，该框架融合了自监督偏差学习方案来捕获并利用此类偏差。ST-SSDL将每个输入锚定到其历史平均值，并使用可学习的原型（prototypes）对潜在空间进行离散化，这些原型代表典型的时空模式。我们提出两个辅助目标来完善这一结构：一个对比损失（contrastive loss），增强原型间的可区分性；一个偏差损失（deviation loss），正则化输入表示与对应原型之间的距离一致性以量化偏差。这些组件与预测目标联合优化，引导模型组织其隐藏空间，并提高在不同输入条件下的泛化能力。在六个基准数据集上的实验表明，ST-SSDL在多个指标上持续优于最先进的基线。可视化进一步展示了其在复杂时空场景中自适应响应不同偏差水平的能力。我们的代码和数据集可在 https://github.com/Jimmy-7664/ST-SSDL 获取。
英文摘要：
Spatio-temporal forecasting is essential for real-world applications such as traffic management and urban computing. Although recent methods have shown improved accuracy, they often fail to account for dynamic deviations between current inputs and historical patterns. These deviations contain critical signals that can significantly affect model performance. To fill this gap, we propose ST-SSDL, a Spatio-Temporal time series forecasting framework that incorporates a Self-Supervised Deviation Learning scheme to capture and utilize such deviations. ST-SSDL anchors each input to its historical average and discretizes the latent space using learnable prototypes that represent typical spatio-temporal patterns. Two auxiliary objectives are proposed to refine this structure: a contrastive loss that enhances inter-prototype discriminability and a deviation loss that regularizes the distance consistency between input representations and corresponding prototypes to quantify deviation. Optimized jointly with the forecasting objective, these components guide the model to organize its hidden space and improve generalization across diverse input conditions. Experiments on six benchmark datasets show that ST-SSDL consistently outperforms state-of-the-art baselines across multiple metrics. Visualizations further demonstrate its ability to adaptively respond to varying levels of deviation in complex spatio-temporal scenarios. Our code and datasets are available at https://github.com/Jimmy-7664/ST-SSDL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
