STAN: Spatio-Temporal Attention Network for Next Location Recommendation

Abstract

The next location recommendation is at the core of various location-based applications. Current state-of-the-art models have attempted to solve spatial sparsity with hierarchical gridding and model temporal relation with explicit time intervals, while some vital questions remain unsolved. Non-adjacent locations and non-consecutive visits provide non-trivial correlations for understanding a user's behavior but were rarely considered. To aggregate all relevant visits from user trajectory and recall the most plausible candidates from weighted representations, here we propose a Spatio-Temporal Attention Network (STAN) for location recommendation. STAN explicitly exploits relative spatiotemporal information of all the check-ins with self-attention layers along the trajectory. This improvement allows a point-to-point interaction between non-adjacent locations and non-consecutive check-ins with explicit spatiotemporal effect. STAN uses a bi-layer attention architecture that firstly aggregates spatiotemporal correlation within user trajectory and then recalls the target with consideration of personalized item frequency (PIF). By visualization, we show that STAN is in line with the above intuition. Experimental results unequivocally show that our model outperforms the existing state-of-the-art methods by 9-17%.

Accepted to The Web Conference (WWW2021)

References in corpus (5)

• Session-based Recommendation with Graph Neural Networks
• Session-based Recommendations with Recurrent Neural Networks
• TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation
• Modeling Personalized Item Frequency Information for Next-basket Recommendation
• An Empirical Study on Feature Discretization

Cited by in corpus (20)

• GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
• WorldKG: A World-Scale Geographic Knowledge Graph
• Large Language Models for Next Point-of-Interest Recommendation
• Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction
• A Diffusion model for POI recommendation
• NetTraj: A Network-based Vehicle Trajectory Prediction Model with Directional Representation and Spatiotemporal Attention Mechanisms
• Automated Spatio-Temporal Graph Contrastive Learning
• AdaMCT: Adaptive Mixture of CNN-Transformer for Sequential Recommendation
• Hierarchical Transformer with Spatio-Temporal Context Aggregation for Next Point-of-Interest Recommendation
• Empowering Next POI Recommendation with Multi-Relational Modeling
• Modeling Multi-aspect Preferences and Intents for Multi-behavioral Sequential Recommendation
• A Survey on Point-of-Interest Recommendations Leveraging Heterogeneous Data
• Bi-Level Graph Structure Learning for Next POI Recommendation
• Revisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendation
• Activity-aware Human Mobility Prediction with Hierarchical Graph Attention Recurrent Network
• Where have you been? A Study of Privacy Risk for Point-of-Interest Recommendation
• Spatial-Temporal Cross-View Contrastive Pre-training for Check-in Sequence Representation Learning
• SEP-GCN: Leveraging Similar Edge Pairs with Temporal and Spatial Contexts for Location-Based Recommender Systems
• Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems
• An Embarrassingly Simple Rule-based Visiting Circulation Approach to Trip Destination Prediction