Disentangling Multiplex Spatial-Temporal Transition Graph Representation Learning for Socially Enhanced POI Recommendation

2025-08-11

AI Summary

Existing POI recommendation methods model spatial and temporal transitions separately, leading to inconsistent representations of critical spatiotemporal nodes, thereby introducing information redundancy and degrading interpretability. To address this, we propose DiMuST—a social-enhanced next-POI recommendation framework that, for the first time, disentangles shared and private features on a multi-layer spatiotemporal graph. DiMuST employs a Product-of-Experts mechanism to fuse shared representations and introduces contrastive learning constraints to purify private features. It further integrates a disentangled variational multi-relational graph autoencoder with explicit social relation modeling. Extensive experiments on two real-world datasets demonstrate that DiMuST significantly improves recommendation accuracy and robustness over state-of-the-art baselines, while simultaneously enhancing model interpretability through explicit feature disentanglement and socially grounded representation learning.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Next Point-of-Interest (POI) recommendation is a research hotspot in business intelligence, where users' spatial-temporal transitions and social relationships play key roles. However, most existing works model spatial and temporal transitions separately, leading to misaligned representations of the same spatial-temporal key nodes. This misalignment introduces redundant information during fusion, increasing model uncertainty and reducing interpretability. To address this issue, we propose DiMuST, a socially enhanced POI recommendation model based on disentangled representation learning over multiplex spatial-temporal transition graphs. The model employs a novel Disentangled variational multiplex graph Auto-Encoder (DAE), which first disentangles shared and private distributions using a multiplex spatial-temporal graph strategy. It then fuses the shared features via a Product of Experts (PoE) mechanism and denoises the private features through contrastive constraints. The model effectively captures the spatial-temporal transition representations of POIs while preserving the intrinsic correlation of their spatial-temporal relationships. Experiments on two challenging datasets demonstrate that our DiMuST significantly outperforms existing methods across multiple metrics.

Problem

• Separate modeling of spatial-temporal transitions causes misaligned representations
• Redundant information fusion increases model uncertainty and reduces interpretability
• Need for socially enhanced POI recommendation with disentangled spatial-temporal graphs

Innovation

• Disentangled variational multiplex graph Auto-Encoder
• Multiplex spatial-temporal graph strategy
• Product of Experts fusion mechanism