Spatial-Temporal Mixture-of-Graph-Experts for Multi-Type Crime Prediction

TL;DR

This paper introduces a novel framework called ST-MoGE for multi-type crime prediction, effectively capturing diverse spatial-temporal patterns, addressing data imbalance, and outperforming existing methods on real-world datasets.

Contribution

The paper proposes a Spatial-Temporal Mixture-of-Graph-Experts framework with an attentive gating module, contrastive learning, and hierarchical loss re-weighting for improved multi-type crime prediction.

Findings

Outperforms twelve baseline methods on real datasets.

Effectively models diverse crime patterns and spatial-temporal heterogeneity.

Reduces bias and improves learning in data-scarce regions.

Abstract

As various types of crime continue to threaten public safety and economic development, predicting the occurrence of multiple types of crimes becomes increasingly vital for effective prevention measures. Although extensive efforts have been made, most of them overlook the heterogeneity of different crime categories and fail to address the issue of imbalanced spatial distribution. In this work, we propose a Spatial-Temporal Mixture-of-Graph-Experts (ST-MoGE) framework for collective multiple-type crime prediction. To enhance the model's ability to identify diverse spatial-temporal dependencies and mitigate potential conflicts caused by spatial-temporal heterogeneity of different crime categories, we introduce an attentive-gated Mixture-of-Graph-Experts (MGEs) module to capture the distinctive and shared crime patterns of each crime category. Then, we propose Cross-Expert Contrastive Learning(CECL) to update the MGEs and force each expert to focus on specific pattern modeling, thereby reducing blending and redundancy. Furthermore, to address the issue of imbalanced spatial distribution, we propose a Hierarchical Adaptive Loss Re-weighting (HALR) approach to eliminate biases and insufficient learning of data-scarce regions. To evaluate the effectiveness of our methods, we conduct comprehensive experiments on two real-world crime datasets and compare our results with twelve advanced baselines. The experimental results demonstrate the superiority of our methods.