POI-Enhancer: An LLM-based Semantic Enhancement Framework for POI Representation Learning

2025-02-14

AI Summary

To address the weak semantic representation of points-of-interest (POIs) in POI representation learning, this paper proposes a plug-and-play large language model (LLM)-enhanced framework. The method employs domain-specific prompting to extract fine-grained semantic knowledge about POIs, incorporates dual-feature alignment and semantic feature fusion modules to ensure knowledge fidelity and completeness, and integrates cross-attention mechanisms with multi-view contrastive learning to inject semantics while enabling human-interpretable modeling. Crucially, the framework operates without LLM fine-tuning, ensuring strong generalizability and deployment flexibility. Extensive experiments on three real-world trajectory datasets demonstrate significant improvements over state-of-the-art baselines across downstream tasks—including POI recommendation and trajectory prediction—validating both the effectiveness and robustness of the proposed semantic enhancement.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

POI representation learning plays a crucial role in handling tasks related to user mobility data. Recent studies have shown that enriching POI representations with multimodal information can significantly enhance their task performance. Previously, the textual information incorporated into POI representations typically involved only POI categories or check-in content, leading to relatively weak textual features in existing methods. In contrast, large language models (LLMs) trained on extensive text data have been found to possess rich textual knowledge. However leveraging such knowledge to enhance POI representation learning presents two key challenges: first, how to extract POI-related knowledge from LLMs effectively, and second, how to integrate the extracted information to enhance POI representations. To address these challenges, we propose POI-Enhancer, a portable framework that leverages LLMs to improve POI representations produced by classic POI learning models. We first design three specialized prompts to extract semantic information from LLMs efficiently. Then, the Dual Feature Alignment module enhances the quality of the extracted information, while the Semantic Feature Fusion module preserves its integrity. The Cross Attention Fusion module then fully adaptively integrates such high-quality information into POI representations and Multi-View Contrastive Learning further injects human-understandable semantic information into these representations. Extensive experiments on three real-world datasets demonstrate the effectiveness of our framework, showing significant improvements across all baseline representations.

Problem

• Enhance POI representation learning
• Extract POI-related knowledge from LLMs
• Integrate multimodal information effectively

Innovation

• LLM-based semantic enhancement
• Dual Feature Alignment module
• Cross Attention Fusion module