Multi-Graph Fusion Networks for Urban Region Embedding
This work addresses urban planning and safety applications by providing better region embeddings for tasks such as crime prediction, but it appears incremental as it builds on existing graph-based methods for mobility data.
The paper tackles the problem of learning urban region embeddings from human mobility data to enable cross-domain prediction tasks like crime prediction, and the proposed Multi-Graph Fusion Networks (MGFN) achieve up to a 12.35% improvement over state-of-the-art methods in experiments.
Learning the embeddings for urban regions from human mobility data can reveal the functionality of regions, and then enables the correlated but distinct tasks such as crime prediction. Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks. In this paper, we propose multi-graph fusion networks (MGFN) to enable the cross domain prediction tasks. First, we integrate the graphs with spatio-temporal similarity as mobility patterns through a mobility graph fusion module. Then, in the mobility pattern joint learning module, we design the multi-level cross-attention mechanism to learn the comprehensive embeddings from multiple mobility patterns based on intra-pattern and inter-pattern messages. Finally, we conduct extensive experiments on real-world urban datasets. Experimental results demonstrate that the proposed MGFN outperforms the state-of-the-art methods by up to 12.35% improvement.