English

RecMind: LLM-Enhanced Graph Neural Networks for Personalized Consumer Recommendations

Machine Learning 2025-09-09 v1

Abstract

Personalization is a core capability across consumer technologies, streaming, shopping, wearables, and voice, yet it remains challenged by sparse interactions, fast content churn, and heterogeneous textual signals. We present RecMind, an LLM-enhanced graph recommender that treats the language model as a preference prior rather than a monolithic ranker. A frozen LLM equipped with lightweight adapters produces text-conditioned user/item embeddings from titles, attributes, and reviews; a LightGCN backbone learns collaborative embeddings from the user-item graph. We align the two views with a symmetric contrastive objective and fuse them via intra-layer gating, allowing language to dominate in cold/long-tail regimes and graph structure to stabilize rankings elsewhere. On Yelp and Amazon-Electronics, RecMind attains the best results on all eight reported metrics, with relative improvements up to +4.53\% (Recall@40) and +4.01\% (NDCG@40) over strong baselines. Ablations confirm both the necessity of cross-view alignment and the advantage of gating over late fusion and LLM-only variants.

Keywords

Cite

@article{arxiv.2509.06286,
  title  = {RecMind: LLM-Enhanced Graph Neural Networks for Personalized Consumer Recommendations},
  author = {Chang Xue and Youwei Lu and Chen Yang and Jinming Xing},
  journal= {arXiv preprint arXiv:2509.06286},
  year   = {2025}
}
R2 v1 2026-07-01T05:25:32.899Z