Improving the spatial–temporal aware attention network with dynamic trajectory graph learning for next Point-Of-Interest recommendation. Issue 3 (May 2023)

• Record Type: Journal Article
• Authors: Cao, Gang; Cui, Shengmin; Joe, Inwhee
• Is Part Of: Information processing & management. Volume 60:Issue 3(2023)
• Publication Date: 2023-05
• Subjects: Point-Of-Interest -- Attention mechanism -- Graph convolution -- Dynamic user preference modeling; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2023.103335
• Languages: English
• ISSNs: 0306-4573

Abstract

Abstract: Next Point-Of-Interest (POI) recommendation aim to predict users' next visits by mining their movement patterns. Existing works attempt to extract spatial–temporal relationships from historical check-ins; however, the following critical factors have not been adequately considered: (1) structured features implied in trajectory that reflect individual visit tendency; (2) collaborative signals from other users and (3) dynamic user preference. To this end, we jointly take into full consideration the graph-structured information as well as sequential effects of user trajectory sequences and propose the Trajectory Graph enhanced Spatial–Temporal aware Attention Network (TGSTAN). Given the general preference among users and the shifts of individual interests over time, we present a novel trajectory-aware dynamic graph convolution network module (TDGCN) to facilitate the capturing of local spatial correlations. Specifically, TDGCN dynamically adjusts the normalized adjacency matrix of the trajectory graph by element-wise multiplication with self-attentive POI representations. The local trajectory graph is generated from the same training batch to reflect real-time and collaborative signals, while also following causality. Moreover, we explicitly integrate spatial–temporal interval information with bilinear interpolation to comprehensively attach relative proximity to attention mechanism when capturing long-term dependence. Extensive experiments on three real-world Location-Based Social Networks datasets (Foursquare_TKY, Weeplaces and Gowalla_CA) demonstrate that the proposed TGSTAN consistently outperforms the existing state-of-the-art baselines with an average of 8.18%, 6.59%, and 9.60% improvement on the three datasets, respectively. Highlights: Collaborative signals and dynamic user preference are considered in graph learning. The relative proximity of spatial–temporal interval is explicitly emphasized. A model combining self-attention and GCN is proposed for Next POI Recommendation. The effectiveness and stability of the model are verified by a series of experiments.