SPRIG：基于语义ID增强路径的知识图谱生成式推荐
SPRIG: Semantic-ID-enhanced Paths for Knowledge Graph-based Generative Recommendation
浏览论文内容
中文总结 AI 辅助
提出SPRIG，一种将内容派生的语义ID集成到知识图谱路径推理中的生成式推荐器，结合两者优势，在电影和音乐数据集上以更少参数和计算成本取得竞争性能。
中文摘要 AI 辅助
利用生成模型的推荐系统通常直接生成项目标识符，而不是通过推荐分数对目录项目进行排序。近期工作超越了纯粹的序列交互信号，通过整合项目内容和项目间的结构化关系，出现了两个不同的方向。语义ID（SIDs）通过用从项目内容中导出的分层量化离散代码替换不透明的、随机初始化的嵌入来丰富项目表示。知识图谱（KG）路径推理则生成实体-关系路径，将推荐基于项目、属性和外部实体之间的结构化关系，从而丰富关系上下文。这两条路线具有互补的局限性：基于SID的模型缺乏关系基础，而基于KG的生成式推荐器仍将项目表示为任意的、不透明的标记，并绑定到大型嵌入表，限制了参数共享和泛化能力。我们提出SPRIG，一种将内容派生的SID集成到KG路径推理中的生成式推荐器。SPRIG在信息丰富的KG路径上进行训练，这些路径以表示为离散的、内容派生的标记的项目终止，结合了两种方法的优点。我们在电影和音乐推荐数据集上，针对涵盖序列语言模型、KG增强方法和基于SID的方法的基线评估了SPRIG。我们的结果表明，SPRIG在参数更少、计算成本更低的情况下，实现了优于先前生成模型的竞争性能。代码：此https URL。
英文摘要
Recommender systems leveraging generative models often generate item identifiers directly, rather than ranking catalog items by a recommendation score. Recent work extends beyond pure sequential interaction signals by incorporating item content and structured relationships among items, with two distinct directions emerging. Semantic IDs (SIDs) enrich item representations by replacing opaque, randomly initialized embeddings with hierarchically quantized discrete codes derived from item content. Knowledge-graph (KG) path reasoning instead generates entity-relation paths that ground recommendations in structured relationships between items, attributes, and external entities, thereby enriching the relational context. These two lines have complementary limitations: SID-based models lack relational grounding, while KG-based generative recommenders still represent items as arbitrary, opaque tokens tied to large embedding tables, limiting parameter sharing and generalization. We propose SPRIG, a generative recommender that integrates content-derived SIDs into KG path reasoning. SPRIG is trained on information-rich KG paths that terminate in items represented as discrete, content-derived tokens, combining the advantages of both approaches. We evaluate SPRIG on movie and music recommendation datasets against baselines spanning sequential language models, KG-augmented methods, and SID-based approaches. Our results show that SPRIG achieves competitive performance over prior generative models while using fewer parameters and a lower compute cost. Code: https://github.com/justinhangoebl/semantic-id-knowledge-graph-recommender
发表机构
- Johannes Kepler University（约翰·开普勒林茨大学）
- Albatross AI（信天翁人工智能）
- Criteo AI Lab（Criteo人工智能实验室）
- Linz Institute of Technology（林茨工业大学）
机构由 AI 辅助整理，请以论文原文为准。
