用大模型生成的语义和地理信息增强推荐，解决冷启动问题。
POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment
- 构建语义与地理双辅助图，融合大模型生成的摘要和位置距离。
- 对比学习对齐行为、语义与空间表征，提升冷启动项推荐效果。
- 在Yelp数据集上召回率提升52.0%，适合处理低交互场景的推荐任务。
基于图神经网络的地点推荐模型虽能有效传播用户-项目交互中的协同信号，但面临冷启动问题：交互稀少或无交互的项目难以被表征。本文提出LLM-augmented Multi-Graph Contrastive Learning（LLM-MGCL），一种多图神经网络，通过项目语义与空间信息扩展LightGCN主干网络。引入两个辅助项目-项目图：由大模型生成的图片摘要与关键词的句向量构建的语义图，以及基于哈弗辛距离计算的地理图。项目嵌入在三个图上并行传播，加性融合，并通过双向InfoNCE对比目标在视图间对齐，连接同一项目的用户行为、语义与空间表示。在Yelp Multimodal Recommendation Dataset上的实验表明，LLM-MGCL显著优于经典协同过滤、矩阵分解及仅依赖交互的图神经网络基线，在召回率@20上比LightGCN提升52.0%，NDCG@20提升64.8%，与最强对比基线SGL相当，而后者同样受冷启动影响。消融研究显示，跨视图对比对齐（CA）是性能提升的主要驱动力，三图联合使用时表现最佳。结果表明，外部知识驱动的大模型生成项目信息可有效弥补缺失协同信号，缓解地点推荐中的项目冷启动问题。
原文摘要 · Abstract (English)
Point-of-interest (POI) recommendation models based on graph neural networks achieve strong performance by propagating collaborative signals over user-item interactions, yet they struggle with the cold-start problem, where items with few or no interactions are not represented. In this paper, we propose LLM-augmented Multi-Graph Contrastive Learning (LLM-MGCL), a multi-graph neural network that uses semantic and spatial information about items to extend the LightGCN backbone with two auxiliary item-item graphs: a semantic graph constructed from sentence embeddings of LLM-generated photo summaries and keywords, and a geographic graph derived from Haversine distances between business locations. Item embeddings are propagated over all three graphs in parallel, fused additively, and aligned across views through a bidirectional InfoNCE contrastive objective that connects behavioral, semantic, and spatial representations of the same items. Experiments on the Yelp Multimodal Recommendation Dataset show that LLM-MGCL outperforms classical collaborative filtering, matrix factorization, and interaction-only graph neural network baselines. It improves Recall@20 by 52.0% and NDCG@20 by 64.8% over LightGCN while performing on par with the strongest contrastive baseline, Self-supervised Graph Learning (SGL), which is also affected by the cold-start problem. An ablation study reveals that the cross-view contrastive alignment (CA) is the primary driver of these gains, with the best performance achieved when all three graphs are combined. Our results suggest that externally grounded, LLM-derived item knowledge can effectively compensate for missing collaborative signal and mitigate the item cold-start problem in POI recommendation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。