SEP-GCN: Leveraging Similar Edge Pairs with Temporal and Spatial Contexts for Location-Based Recommender Systems

2025-06-19

AI Summary

Existing location-aware recommendation models predominantly focus on node representations or isolated edge attributes, neglecting semantic correlations among user-item interaction edges—thereby limiting their capacity to model long-range preferences. To address this, we propose the Edge-Contextualized Graph (ECG), a novel graph structure dynamically constructed from semantically similar edge pairs identified via temporal proximity and geographic closeness. We further design an edge-aware convolution mechanism that enables relation-driven, edge-level message passing. Our method jointly integrates spatiotemporal context modeling, edge-level similarity measurement, and dynamic graph updating. Extensive experiments on multiple benchmark datasets demonstrate significant improvements over state-of-the-art baselines, particularly in sparse and highly dynamic scenarios—yielding enhanced prediction accuracy and robustness. These results empirically validate the critical importance of explicitly modeling inter-edge semantic relationships for location-aware recommendation.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Recommender systems play a crucial role in enabling personalized content delivery amidst the challenges of information overload and human mobility. Although conventional methods often rely on interaction matrices or graph-based retrieval, recent approaches have sought to exploit contextual signals such as time and location. However, most existing models focus on node-level representation or isolated edge attributes, underutilizing the relational structure between interactions. We propose SEP-GCN, a novel graph-based recommendation framework that learns from pairs of contextually similar interaction edges, each representing a user-item check-in event. By identifying edge pairs that occur within similar temporal windows or geographic proximity, SEP-GCN augments the user-item graph with contextual similarity links. These links bridge distant but semantically related interactions, enabling improved long-range information propagation. The enriched graph is processed via an edge-aware convolutional mechanism that integrates contextual similarity into the message-passing process. This allows SEP-GCN to model user preferences more accurately and robustly, especially in sparse or dynamic environments. Experiments on benchmark data sets show that SEP-GCN consistently outperforms strong baselines in both predictive accuracy and robustness.

Problem

• Enhances recommendation by leveraging similar edge pairs in graphs
• Improves modeling of user preferences in sparse environments
• Integrates temporal and spatial contexts for better recommendations

Innovation

• Leverages similar edge pairs with contexts
• Augments graph with similarity links
• Edge-aware convolutional message-passing