Multi-behavior recommendation with SVD Graph Neural Networks

Shengxi Fu, Qianqian Ren, Xingfeng Lv, Jinbao Li

Abstract: Highlights•Proposing a novel contrastive learning paradigm for multi-behavior recommendation.•Solving the data sparsity and noise problem simultaneously.•Adopting SVD method for graph augmentation to enhance model performance.•Experiments on real-world datasets show the superiority of the proposed model.