发表机构
The University of Sydney; Nankai University（悉尼大学; 南开大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对稀疏推荐中整合GNN与LLM优势的挑战，提出TRWH框架，通过随机游走增强融合文本概要与异构图结构，含嵌入创建、异构图神经网络、随机游走路径构建三组件，实验表明其在时尚和美妆数据集上性能远超现有方法。
AI 中文摘要
图神经网络（GNN）和大语言模型（LLM）分别通过对结构和语义信号建模推动了推荐系统的发展。然而，整合它们的互补优势仍具挑战，尤其是在保持语义精度至关重要的稀疏环境中。我们提出了TRWH（文本驱动随机游走异构图神经网络），这是一个通过策略性随机游走增强将LLM生成的文本概要与异构图结构融合的新颖框架。TRWH由三个核心组件组成：嵌入创建，使用Word2Vec和基于LLM的概要分析生成用户和项目表示；异构图神经网络，在多关系边之间传播信息；基于随机游走的路径构建，用二阶用户-用户和项目-项目链接丰富稀疏图。在亚马逊2023时尚（200万用户，82.5万件商品）和美妆（63.1万用户，11.2万件商品）数据集上的实验表明，TRWH比现有方法有显著的性能提升，包括时尚数据集上RMSE降低80.0%、MAE降低52.6%，美妆数据集上分别有25.7%和10.8%的提升。值得注意的是，虽然随机游走与传统嵌入一起提高了性能，但它们会稀释LLM学到的细微表示，凸显了自适应整合策略的重要性。
英文摘要
Graph Neural Networks (GNNs) and Large Language Models (LLMs) have each advanced recommendation systems by modeling structural and semantic signals, respectively. However, integrating their complementary strengths remains challenging, particularly in sparse settings where maintaining semantic precision is critical. We propose TRWH (Text-driven Random Walk Heterogeneous Graph Neural Network), a novel framework that fuses LLM-generated textual profiles with heterogeneous graph structures through strategic random walk augmentation. TRWH consists of three core components: (1) Embedding Creation, which produces user and item representations using both Word2Vec and LLM-based profiling; (2) a Heterogeneous Graph Neural Network (HeteroGNN) that propagates information across multi-relational edges; and (3) Random Walk-based Path Construction, which enriches sparse graphs with second-order user-user and item-item links. Experiments on the Amazon-2023 Fashion (2M users, 825K items) and Beauty (631K users, 112K items) datasets demonstrate that TRWH achieves substantial performance gains over state-of-the-art methods, including 80.0% RMSE and 52.6% MAE reductions on Fashion, and 25.7% and 10.8% improvements on Beauty. Notably, while random walks improve performance with traditional embeddings, they can dilute the nuanced representations learned by LLMs, underscoring the importance of adaptive integration strategies.
