Problem
Research questions and friction points this paper is trying to address.
Human Mobility Patterns
Activity-Location Dynamics
Urban Planning and Services
Activity-Aware Human Mobility Prediction With Hierarchical Graph Attention Recurrent Network
🤖 AI Summary
Existing mobility prediction methods overlook activity semantics and their deep coupling with temporal and spatial contexts, leading to inadequate modeling of individual preferences and limiting applications in urban planning and intelligent transportation. To address this, we propose Activity-GNN: a hierarchical time–activity–location graph structure that explicitly captures complex interdependencies among these dimensions; a novel hierarchical graph attention mechanism enabling cross-granularity relational aggregation; model-agnostic historical-enhanced confidence labeling (MAHEC) to improve robustness; and activity prediction as a multi-task auxiliary objective to strengthen location prediction. Evaluated on two real-world datasets under both recurrent and exploratory mobility scenarios, Activity-GNN achieves an average 12.6% improvement in Top-1 accuracy over state-of-the-art methods, demonstrating the critical role of activity semantics in human mobility modeling.
📝 Abstract
Human mobility prediction is a fundamental task essential for various applications in urban planning, location-based services and intelligent transportation systems. Existing methods often ignore activity information crucial for reasoning human preferences and routines, or adopt a simplified representation of the dependencies between time, activities and locations. To address these issues, we present Hierarchical Graph Attention Recurrent Network (HGARN) for human mobility prediction. Specifically, we construct a hierarchical graph based on past mobility records and employ a Hierarchical Graph Attention Module to capture complex time-activity-location dependencies. This way, HGARN can learn representations with rich human travel semantics to model user preferences at the global level. We also propose a model-agnostic history-enhanced confidence (MAHEC) label to incorporate each user's individual-level preferences. Finally, we introduce a Temporal Module, which employs recurrent structures to jointly predict users' next activities and their associated locations, with the former used as an auxiliary task to enhance the latter prediction. For model evaluation, we test the performance of HGARN against existing state-of-the-art methods in both the recurring (i.e., returning to a previously visited location) and explorative (i.e., visiting a new location) settings. Overall, HGARN outperforms other baselines significantly in all settings based on two real-world human mobility data benchmarks. These findings confirm the important role that human activities play in determining mobility decisions, illustrating the need to develop activity-aware intelligent transportation systems. Source codes of this study are available at https://github.com/YihongT/HGARN.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Hierarchical Graph Attention
Recurrent Network
Temporal Module
🔎 Similar Papers
No similar papers found.
