KGNext: Knowledge-Graph-Enhanced Transformer for Next POI Recommendation With Uncertain Check-Ins

The next point-of-interest (POI) recommendation aims to predict users’ future movements based on their historical trajectories. However, in reality, users may provide uncertain check-in records, resulting in uploaded data that lack precise location information and is instead ambiguous. Despite this challenge, only a limited number of studies have addressed this issue, often overlooking the intricate interactions among users, POIs, and POI categories. To that end, we propose a novel model called knowledge-graph-enhanced transformer (KGNext). KGNext leverages transition and interaction graphs derived from our constructed transitional-interactive knowledge graph (TIKG) to uncover both general movement patterns and varied user preferences regarding POIs and POI categories. Furthermore, KGNext integrates comprehensive contextual information from historical trajectories with TIKG to generate user trajectory embeddings. These encoded features are then utilized by a transformer model to provide fine-grained predictions of the next POI. Experimental results on three real-world datasets demonstrate the superiority of KGNext.

I. Introduction

The past few years have seen notable progress in the development of location-based social networks (LBSNs). The encouragement of users to share their experiences when visiting points of interest (POIs) has resulted in the accumulation of large amounts of historical check-in data on LBSNs. This creates an opportunity to recommend POIs that users might want to visit during their next move [1].