# Learning A Universal Crime Predictor with Knowledge-guided Hypernetworks

arXiv: https://arxiv.org/abs/2511.02336 · HTML: https://mlsanity.com/paper/2511.02336/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 53 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 29 of 29)

- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks](https://mlsanity.com/paper/2005.11650/) (2020)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2007.02901/) (2020)
- [UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction](https://mlsanity.com/paper/2402.11838/) (2024)
- [UrbanGPT: Spatio-Temporal Large Language Models](https://mlsanity.com/paper/2403.00813/) (2024)
- [A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting](https://mlsanity.com/paper/2006.11583/) (2020)
- [Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction](https://mlsanity.com/paper/2204.08587/) (2022)
- [Spatial-Temporal Sequential Hypergraph Network for Crime Prediction with Dynamic Multiplex Relation Learning](https://mlsanity.com/paper/2201.02435/) (2022)
- [Multi-Graph Fusion Networks for Urban Region Embedding](https://mlsanity.com/paper/2201.09760/) (2022)
- [Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs](https://mlsanity.com/paper/2001.02332/) (2020)
- [HAGEN: Homophily-Aware Graph Convolutional Recurrent Network for Crime Forecasting](https://mlsanity.com/paper/2109.12846/) (2021)
- [UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction](https://mlsanity.com/paper/2306.11443/) (2023)
- [Explainable Spatio-Temporal Graph Neural Networks](https://mlsanity.com/paper/2310.17149/) (2023)
- [Spatio-Temporal Meta Contrastive Learning](https://mlsanity.com/paper/2310.17678/) (2023)
- [Crime Prediction Using Machine Learning and Deep Learning: A Systematic Review and Future Directions](https://mlsanity.com/paper/2303.16310/) (2023)
- [Multi-scale Traffic Pattern Bank for Cross-city Few-shot Traffic Forecasting](https://mlsanity.com/paper/2402.00397/) (2024)
- [Hate Speech Detection with Generalizable Target-aware Fairness](https://mlsanity.com/paper/2406.00046/) (2024)
- [Start from Zero: Triple Set Prediction for Automatic Knowledge Graph Completion](https://mlsanity.com/paper/2406.18166/) (2024)
- [AIST: An Interpretable Attention-based Deep Learning Model for Crime Prediction](https://mlsanity.com/paper/2012.08713/) (2020)
- [Semantic-Fused Multi-Granularity Cross-City Traffic Prediction](https://mlsanity.com/paper/2302.11774/) (2023)
- [Frequency Enhanced Pre-training for Cross-city Few-shot Traffic Forecasting](https://mlsanity.com/paper/2406.02614/) (2024)
- [Physics-guided Active Sample Reweighting for Urban Flow Prediction](https://mlsanity.com/paper/2407.13605/) (2024)
- [Spatial-Temporal Meta-path Guided Explainable Crime Prediction](https://mlsanity.com/paper/2205.01901/) (2022)
- [Target inductive methods for zero-shot regression](https://mlsanity.com/paper/2402.01252/) (2024)
- [Memory-enhanced Invariant Prompt Learning for Urban Flow Prediction under Distribution Shifts](https://mlsanity.com/paper/2412.05534/) (2024)

## Abstract (arXiv)

Predicting crimes in urban environments is crucial for public safety, yet existing prediction methods often struggle to align the knowledge across diverse cities that vary dramatically in data availability of specific crime types. We propose HYpernetwork-enhanced Spatial Temporal Learning (HYSTL), a framework that can effectively train a unified, stronger crime predictor without assuming identical crime types in different cities' records. In HYSTL, instead of parameterising a dedicated predictor per crime type, a hypernetwork is designed to dynamically generate parameters for the prediction function conditioned on the crime type of interest. To bridge the semantic gap between different crime types, a structured crime knowledge graph is built, where the learned representations of crimes are used as the input to the hypernetwork to facilitate parameter generation. As such, when making predictions for each crime type, the predictor is additionally guided by its intricate association with other relevant crime types. Extensive experiments are performed on two cities with non-overlapping crime types, and the results demonstrate HYSTL outperforms state-of-the-art baselines.