IReGNN: Implicit review-enhanced graph neural network for explainable recommendation

Open Webpage

Qingbo Hao, Chundong Wang, Yingyuan Xiao, Wenguang Zheng

Published: 01 Jan 2025, Last Modified: 05 Nov 2025Knowl. Based Syst. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•An Implicit Review-enhanced Graph Neural Network is proposed for explainable recommendations.•Implicit relationships can alleviate data sparsity while filtering out noise.•The exploration of topics is necessary to enhance recommendation performance.•Topic features and implicit relationships can facilitate explanation generation.