Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach
This work addresses spatio-temporal prediction problems for applications like intelligent transportation and weather forecasting, representing a novel method for known bottlenecks.
The paper tackles challenges in spatio-temporal prediction, such as inadequate multi-modal fusion, confounding factors, and high computational complexity, by proposing E^2-CSTP, which achieves up to 9.66% accuracy improvements and 17.37%-56.11% reductions in computational overhead compared to state-of-the-art methods.
Spatio-temporal prediction plays a crucial role in intelligent transportation, weather forecasting, and urban planning. While integrating multi-modal data has shown potential for enhancing prediction accuracy, key challenges persist: (i) inadequate fusion of multi-modal information, (ii) confounding factors that obscure causal relations, and (iii) high computational complexity of prediction models. To address these challenges, we propose E^2-CSTP, an Effective and Efficient Causal multi-modal Spatio-Temporal Prediction framework. E^2-CSTP leverages cross-modal attention and gating mechanisms to effectively integrate multi-modal data. Building on this, we design a dual-branch causal inference approach: the primary branch focuses on spatio-temporal prediction, while the auxiliary branch mitigates bias by modeling additional modalities and applying causal interventions to uncover true causal dependencies. To improve model efficiency, we integrate GCN with the Mamba architecture for accelerated spatio-temporal encoding. Extensive experiments on 4 real-world datasets show that E^2-CSTP significantly outperforms 9 state-of-the-art methods, achieving up to 9.66% improvements in accuracy as well as 17.37%-56.11% reductions in computational overhead.