摘要： 准确的交通速度预测对提高智能交通系统的效率至关重要。然而，当前端到端的交通速度预测模型往往受限于特定区域或特定时间段的交通速度数据训练，泛化能力有限，且多数方法使用静态网络结构和节点参数共享机制，难以捕捉动态交通特性和节点多样性。针对这两个挑战，本文提出了一种基于自适应时空掩蔽预训练的交通速度预测方法（Adaptive Spatial-temporal Masking Pre-training for Traffic Speed Prediction，ASTMP），分为自适应时空掩蔽预训练阶段和预测阶段。在预训练阶段，本文设计了动态自适应图卷积层，为每个节点提供了权重参数和偏差参数，并依据包含节点独特属性的节点嵌入矩阵构建自适应图，深入挖掘节点的独特属性与节点间关系的动态规律。其次，设计时空掩蔽编码层对长时间交通速度序列进行随机时空掩蔽处理。然后，设计时空掩蔽解码层利用掩蔽令牌替换被掩蔽位置的数据，根据上下文信息重构被掩蔽的信息，增强方法的适应能力和泛化能力。在预测阶段，本文将预训练阶段学习到的长时间交通速度序列中蕴含的动态时空信息，与短时间交通速度预测器结合，实现更精准和高效的预测。在METR-LA、PEMS-BAY数据集上的实验结果表明，ASTMP的预测性能优于现有的先进基线方法，验证了方法可行性与有效性。

Abstract: Accurate traffic speed prediction is critical for enhancing the efficiency of Intelligent Transportation Systems (ITS). However, contemporary end-to-end prediction models are often constrained by training data from specific regions or time periods, leading to limited generalization capabilities. Furthermore, most existing methods employ static network structures and parameter-sharing mechanisms, which struggle to capture dynamic traffic characteristics and the inherent diversity across different nodes. To address these two challenges, this paper proposes Adaptive Spatial-Temporal Masking Pre-training for Traffic Speed Prediction (ASTMP), which is divided into a pre-training stage and a prediction stage. In the pre-training stage, a dynamic adaptive graph convolutional layer is designed to provide unique weight and bias parameters for each node. By constructing an adaptive graph based on a node embedding matrix containing individual node attributes, the unique properties of nodes and the dynamic patterns governing their inter-relationships can be deeply explored. Subsequently, a spatial-temporal masking encoding layer is developed to perform random masking on long-term traffic speed sequences. A corresponding decoding layer then utilizes mask tokens to replace data at masked positions, reconstructing the original information based on contextual cues to enhance the model's adaptability and generalization performance. In the prediction stage, the dynamic spatial-temporal representations learned from long-term sequences are integrated with a short-term traffic speed predictor to achieve more precise and efficient forecasting. Experimental results on the METR-LA and PEMS-BAY datasets demonstrate that ASTMP outperforms state-of-the-art baseline methods, validating the feasibility and effectiveness of the proposed approach.