GMR-Rec: Graph mutual regularization learning for multi-domain recommendation

Yifan Wang, Yangzi Yang, Shuai Li, Yutao Xie, Zhiping Xiao, Ming Zhang, Wei Ju

Abstract: Highlights•We propose a novel multi-domain framework to address the cold-start problem.•We propose a Parallel GNN to exploit the heterogeneous nature of the graph.•We design a graph mutual regularization framework to distinguish user interests.•Experimental results on four datasets highlight the superiority of our model.