Dynamic Spatial-Temporal Memory Augmentation Network for Traffic Prediction

Traffic flow prediction plays a crucial role in the development of smart cities. However, existing studies face challenges in effectively capturing spatio-temporal contexts, handling hierarchical temporal features, and understanding spatial heterogeneity. To better manage the spatio-temporal correlations inherent in traffic flow, we present a novel model called <b>D</b>ynamic <b>S</b>patio-<b>T</b>emporal <b>M</b>emory-<b>A</b>ugmented <b>N</b>etwork (<b>DSTMAN</b>). Firstly, we design three spatial-temporal embeddings to capture dynamic spatial-temporal contexts and encode the unique characteristics of time units and spatial states. Secondly, these three spatial-temporal components are integrated to form a multi-scale spatial-temporal block, which effectively extracts hierarchical spatial-temporal dependencies. Finally, we introduce a meta-memory node bank to construct an adaptive neighborhood graph, implicitly representing spatial relationships and enhancing the learning of spatial heterogeneity through a secondary memory mechanism. Evaluation on four public datasets, including METR-LA and PEMS-BAY, demonstrates that the proposed model outperforms benchmark models such as MTGNN, DCRNN, and AGCRN. On the METR-LA dataset, our model reduces the MAE by 4% compared to MTGNN, 6.9% compared to DCRNN, and 5.8% compared to AGCRN, confirming its efficacy in traffic flow prediction.