Review
Open access
Sep 2026
LRGCL: LLM-refined graph contrastive learning for review-based recommendation
LRGCL is proposed, an LLM-Refined Graph Contrastive Learning model for personalized recommendation that introduces a semantic-preserving contrastive objective in which key interaction edges are identified and preserved in augmented graph views, while only non-critical edges are dropped.
Li-Ye Shi, Peng-Fei Shao, Shao-Zhong Zhang et al.
· Journal of King Saud Univers... · 0 citations