HAGEN: Homophily-Aware Graph Convolutional Recurrent Network for Crime Forecasting

Abstract

The crime forecasting is an important problem as it greatly contributes to urban safety. Typically, the goal of the problem is to predict different types of crimes for each geographical region (like a neighborhood or censor tract) in the near future. Since nearby regions usually have similar socioeconomic characteristics which indicate similar crime patterns, recent state-of-the-art solutions constructed a distance-based region graph and utilized Graph Neural Network (GNN) techniques for crime forecasting, because the GNN techniques could effectively exploit the latent relationships between neighboring region nodes in the graph if the edges reveal high dependency or correlation. However, this distance-based predefined graph cannot fully capture crime correlation between regions that are far from each other but share similar crime patterns. Hence, to make an accurate crime prediction, the main challenge is to learn a better graph that reveals the dependencies between regions in crime occurrences and meanwhile captures the temporal patterns from historical crime records. To address these challenges, we propose an endto-end graph convolutional recurrent network called HAGEN with several novel designs for crime prediction. Specifically, our framework could jointly capture the crime correlation between regions and the temporal crime dynamics by combining an adaptive region graph learning module with the Diffusion Convolution Gated Recurrent Unit (DCGRU). Based on the homophily assumption of GNN (i.e., graph convolution works better where neighboring nodes share the same label), we propose a homophily-aware constraint to regularize the optimization of the region graph so that neighboring region nodes on the learned graph share similar crime patterns, thus fitting the mechanism of diffusion convolution. It also incorporates crime embedding to model the interdependencies between regions and crime categories. Empirical experiments and comprehensive analysis on two real-world datasets showcase the effectiveness of HAGEN.Preprint. Under review.

Crime prediction with graph neural networks and multivariate normal distributions

“…Another study [11] implemented gated recurrent network with diffusion convolution modules following a multilayer perceptron (MLP). Recently, [12] have introduced a homophily-aware constraint on the loss function so that neighboring region nodes share similar crime patterns. Nevertheless, these works are not generative and work on the districts, which causes the complexity and sparsity problems.…”

“…The prior works in the first category [6][7][8][9] divide city area into a grid, where each cell contains the crime information for each crime category that happened in the past. The works in the second category [10][11][12] divide the city area into unordered regions and create a graph structure that captures the correlations among the regions with corresponding edge weights and node features. However, the regions in both of these approaches correspond to extremely wide sections of the cities.…”