SPRIG: Semantic-ID-enhanced Paths for Knowledge Graph-based Generative Recommendation

2026-10-05

AI Summary

This study addresses the lack of relational grounding in semantic IDs for generative recommendation, as well as the parameter redundancy and limited generalization inherent in conventional knowledge graph approaches. To this end, we propose SPRIG, a model that pioneers the integration of discrete semantic IDs—derived from hierarchical quantized encoding—into knowledge graph path reasoning. Specifically, SPRIG leverages large language models to generate entity-relation paths, replacing traditional embedding tables with discrete tokens to achieve synergistic enhancement of structured relational information and semantic representations. Experimental results demonstrate that SPRIG attains competitive performance on movie and music datasets while substantially reducing both parameter count and computational overhead. These findings validate the feasibility of efficient generative recommendation through the proposed framework.

Abstract

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

Problem

• Generative Recommendation
• Semantic IDs
• Knowledge Graph
• Item Representation
• Parameter Sharing

Innovation

• Generative Recommendation
• Semantic ID
• Knowledge Graph Path Reasoning
• Discrete Tokenization
• Parameter Efficiency