Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a persona-driven session-based recommendation system (SBRS) that leverages LLMs and heterogeneous knowledge graphs (KGs) to model latent user personas. The framework extracts personalized information by constructing a KG initialized with LLM-derived item embeddings and learning user personas using Heterogeneous Deep Graph Infomax (HDGI). Integrating these persona representations into a modified data-driven SBRS architecture improves recommendation accuracy, particularly in sparse data scenarios.
Grounding user persona modeling in structured relational signals from a knowledge graph beats relying solely on sequence modeling or text-based user representations for session-based recommendations.
Session-based recommendation systems (SBRS) aim to capture user's short-term intent from interaction sequences. However, the common assumption of anonymous sessions limits personalization, particularly under sparse or cold-start conditions. Recent advances in LLM-augmented recommendation have shown that LLMs can generate rich item representations, but modeling user personas with LLMs remains challenging due to anonymous sessions. In this work, we propose a persona-driven SBRS framework that explicitly models latent user personas inferred from a heterogeneous knowledge graph (KG) and integrates them into a data-driven recommendation pipeline.Our framework adopts a two-stage architecture consisting of personalized information extraction and personalized information utilization, inspired by recent chain-of-thought recommendation approaches. In the personalized information extraction stage, we construct a heterogeneous KG that integrates time-independent user-item, item-item, item-feature association, and metadata from DBpedia. We then learn latent user personas in an unsupervised manner using a Heterogeneous Deep Graph Infomax (HDGI) objective over a KG initialized with LLM-derived item embeddings. In the personalized information utilization stage, the learned persona representations together with LLM-derived item embeddings are incorporated into a modified architecture of data-driven SBRS to generate a candidate set of relevant items, followed by reranking using the base sequential model to emphasize short-term session intent. Unlike prior approaches that rely solely on sequence modeling or text-based user representations, our method grounds user persona modeling in structured relational signals derived from a KG. Experiments on Amazon Books and Amazon Movies & TV demonstrate that our approach consistently improves over sequential models with user embeddings derived using session history.