FEST: A Multi-way Framework with Enhanced Spatial-Temporal Modeling for Traffic Forecasting

Accurately forecasting traffic flow using time-series data from multimedia sensors remains a significant challenge, despite its importance for advancing intelligent transportation systems. Recent advancements in attention-based models have shown promise in capturing spatial-temporal dependencies in traffic flow data. Yet, these models exhibit three principal limitations: (1) they employ either factorized or coupled spatial-temporal attention mechanisms, potentially failing to fully harness the potential of these distinct approaches; (2) the attention allocation for spatial nodes is predominantly data-centric, which may overlook existing knowledge about the nodes' importance within the transportation network; (3) while traditional attention-based methods effectively capture long-term dependencies, they often struggle with adapting to the disparate lengths of temporal contexts. To overcome these limitations, we introduce a multi-way framework dubbed FEST that innovatively integrates both factorized and coupled spatial-temporal attention mechanisms. We then enhance FEST by incorporating PageRank-derived node importance scores to guide focus on nodes. Moreover, a novel multi-scale temporal learning approach is proposed to improve model capability with both long- and short-term temporal dynamics. Extensive experiments on real-world datasets under long- and short-term prediction scenarios confirm the effectiveness of our method.