IRApr 8

Leveraging LLMs and Heterogeneous Knowledge Graphs for Persona-Driven Session-Based Recommendation

arXiv:2604.0692857.5h-index: 5
AI Analysis

This work addresses personalization challenges in session-based recommendation for e-commerce users, but it is incremental as it builds on existing LLM and knowledge graph methods.

The paper tackles the problem of limited personalization in session-based recommendation systems due to anonymous sessions by proposing a persona-driven framework that models latent user personas from a heterogeneous knowledge graph and integrates them with LLM-derived item embeddings. Experiments on Amazon datasets show consistent improvements over sequential models with user embeddings from session history.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes