arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.02702cs.CEcs.SIstat.ML
收藏

VisitHGNN:用于兴趣点到访模式建模的异构图神经网络

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

College of Engineering, University of Georgia(佐治亚大学工程学院)

Lin Pang, Jidong J. Yang

AI总结:

本研究提出异构图神经网络VisitHGNN,融合多源属性与空间等关联预测POI到访概率,在富尔顿县数据上表现优于基线,可为城市相关领域决策提供支撑。

摘要:

理解城市居民如何在社区与目的地之间出行,对交通规划、出行管理和公共卫生至关重要。通过挖掘城市场所间蕴含空间、时间和功能关联的历史起讫点流量模式,我们估算了从社区到特定目的地的到访概率。这些概率反映了社区层面对全市机动车和步行流量的贡献,可为需求估算、可达性评估和多模式规划提供支撑。\n具体而言,我们提出了VisitHGNN——一种异质的、关系特定的图神经网络,用于预测单个兴趣点(POI)的到访概率。POI通过数值型、JSON衍生型和文本属性进行表征,并补充了POI间空间邻近性、时间共活性和品牌亲和性的固定汇总特征;人口普查区块组(CBG)则由72个社会人口统计变量描述。CBG通过空间邻接关系相连,POI与CBG通过带距离标注的跨类型边连接。推理过程被限制在基于距离筛选的合理来源CBG候选集内,训练阶段通过最小化带掩码的Kullback-Leibler(KL)散度,生成候选集上的概率分布。\n利用美国佐治亚州富尔顿县的每周出行数据,VisitHGNN取得了优异的预测性能:平均KL散度为0.287,平均绝对误差(MAE)为0.008,Top-1准确率为0.853,R平方值为0.892,大幅优于成对MLP和仅基于距离的基线模型,且与实际到访模式高度吻合(NDCG@50=0.966;Recall@5=0.611)。模型输出的概率分布能高保真地还原观测到的出行行为,凸显了其在城市规划、交通政策、出行系统设计和公共卫生领域提供决策支持的潜力。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑