用图文转换方法融合图数据与大模型，提升电商商品组合推荐效果
Dual-Enhancement Product Bundling: Bridging Interactive Graph and Large Language Model
- 将用户交互图结构转为自然语言提示，让大模型理解商品搭配约束
- 在三个数据集上相比顶尖方法提升6.3%-26.5%的推荐准确率
- 适合做电商推荐系统优化的研究者和工程师参考
商品组合推荐能显著提升电商平台收入，但现有方法存在两大挑战：(1) 协同过滤对冷启动商品表现差，因依赖历史交互数据；(2) 大语言模型缺乏直接建模交互图的能力。为此，我们提出一种双增强方法，融合交互图学习与大模型语义理解实现商品组合推荐。该方法引入图到文本范式，通过动态概念绑定机制（DCBM）将图结构转化为自然语言提示，有效对齐领域实体与大模型分词，实现对组合约束的精准理解。在POG、POG_dense和Steam三个基准数据集上的实验表明，该方法相较当前最优基线性能提升6.3%-26.5%。
原文摘要 · Abstract (English)
Product bundling boosts e-commerce revenue by recommending complementary item combinations. However, existing methods face two critical challenges: (1) collaborative filtering approaches struggle with cold-start items owing to dependency on historical interactions, and (2) LLMs lack inherent capability to model interactive graph directly. To bridge this gap, we propose a dual-enhancement method that integrates interactive graph learning and LLM-based semantic understanding for product bundling. Our method introduces a graph-to-text paradigm, which leverages a Dynamic Concept Binding Mechanism (DCBM) to translate graph structures into natural language prompts. The DCBM plays a critical role in aligning domain-specific entities with LLM tokenization, enabling effective comprehension of combinatorial constraints. Experiments on three benchmarks (POG, POG_dense, Steam) demonstrate 6.3%-26.5% improvements over state-of-the-art baselines.
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。