VisitHGNN: Heterogeneous Graph Neural Networks for Modeling Point-of-Interest Visit Patterns

2025-10-02

AI Summary

This paper addresses the challenge of modeling destination visitation probabilities at the community level. We propose VisitHGNN, a heterogeneous graph neural network that constructs a POI graph integrating spatial adjacency, spatiotemporal co-occurrence, and brand affiliation. The model incorporates relation-specific attention mechanisms and a distance-constrained inference module, and employs masked KL-divergence loss alongside 72-dimensional sociodemographic features for multimodal fusion. Evaluated on weekly mobility data from Fulton County, VisitHGNN achieves KL divergence of 0.287, R² of 0.892, Top-1 accuracy of 0.853, and NDCG@50 of 0.966—significantly outperforming all baselines. These results demonstrate substantial improvements in predicting community-level visitation distributions across POIs. The framework enables fine-grained transportation demand estimation, multimodal accessibility assessment, and public health–informed urban planning decisions.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Understanding how urban residents travel between neighborhoods and destinations is critical for transportation planning, mobility management, and public health. By mining historical origin-to-destination flow patterns with spatial, temporal, and functional relations among urban places, we estimate probabilities of visits from neighborhoods to specific destinations. These probabilities capture neighborhood-level contributions to citywide vehicular and foot traffic, supporting demand estimation, accessibility assessment, and multimodal planning. Particularly, we introduce VisitHGNN, a heterogeneous, relation-specific graph neural network designed to predict visit probabilities at individual Points of interest (POIs). POIs are characterized using numerical, JSON-derived, and textual attributes, augmented with fixed summaries of POI--POI spatial proximity, temporal co-activity, and brand affinity, while census block groups (CBGs) are described with 72 socio-demographic variables. CBGs are connected via spatial adjacency, and POIs and CBGs are linked through distance-annotated cross-type edges. Inference is constrained to a distance-based candidate set of plausible origin CBGs, and training minimizes a masked Kullback-Leibler (KL) divergence to yield probability distribution across the candidate set. Using weekly mobility data from Fulton County, Georgia, USA, VisitHGNN achieves strong predictive performance with mean KL divergence of 0.287, MAE of 0.008, Top-1 accuracy of 0.853, and R-square of 0.892, substantially outperforming pairwise MLP and distance-only baselines, and aligning closely with empirical visitation patterns (NDCG@50 = 0.966); Recall@5 = 0.611). The resulting distributions closely mirror observed travel behavior with high fidelity, highlighting the model's potential for decision support in urban planning, transportation policy, mobility system design, and public health.

Problem

• Predicting visit probabilities from neighborhoods to specific points of interest
• Modeling urban mobility patterns using heterogeneous graph neural networks
• Estimating travel behavior for transportation planning and urban management

Innovation

• Heterogeneous graph neural network models POI visit patterns
• POI attributes include spatial, temporal, and brand relations
• Training uses masked KL divergence on distance-constrained candidates