ST-HHOL: Spatio-Temporal Hierarchical Hypergraph Online Learning for Crime Prediction

Keqing Du, Yufan Kang, Xinyu Yang, Wei Shao

Keywords: Crime prediction, Spatio-temporal graph neural networks, Spatio-temporal data mining

TL;DR: We propose ST-HHOL, an online spatio-temporal crime prediction framework that leverages hierarchical hypergraphs to uncover dual-specific patterns and tackle concept drift in non-stationary crime data.

Abstract:

Crime prediction is a critical yet challenging task in urban spatio-temporal forecasting.
Sparse crime records alone are insufficient to capture latent high-order patterns shaped by heterogeneous contextual factors with spatial and criminal specificity, while high non-stationarity renders conventional offline models ineffective against concept drift.
To tackle these challenges, we propose a Spatio-Temporal Hierarchical Hypergraph Online Learning framework named ST-HHOL. First, we propose a hierarchical hypergraph convolution network that integrates crime data with heterogeneous contextual factors to uncover dual-specific crime patterns and their co-occurrence relations. Second, we introduce an iterative online learning strategy to address concept drift by employing frequent fine-tuning for short-term dynamics and periodic retraining for long-term shifts.
Moreover, we adopt a Partially-Frozen LLM that leverages pre-trained sequence priors while adapting its attention mechanisms to crime-specific dependencies, enhancing spatio-temporal reasoning under sparse supervision.
Extensive experiments on three real-world datasets demonstrate that ST-HHOL consistently outperforms state-of-the-art methods in terms of accuracy and robustness, while also providing enhanced interpretability. Code is available at https://github.com/777Rebecca/ST-HHOL.

Primary Area: learning on time series and dynamical systems

Submission Number: 4693